Arabic Cultural Value Alignment
Models classify statements about Arabic culture as true or false. The evaluation covers 58 subject areas.
The authors used GPT-3.5 to generate the statements. The first Open Arabic LLM Leaderboard includes ACVA.
- Made by
- Freedom Intelligence and the AceGPT team
- Released
- September 2023
- Kind
- Knowledge in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Other humanities
- Language
- Arabic
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Qwen2.5-72B #166 on the capability index
- Last model added
- January 2025
- Scores refreshed
- November 20th, 2026
elmrc juhaina tops the leaderboard with 92.9% Qwen2.5-Math-72B-Instruct leads with 73.9% among models released by January 2025
Best score per entry from Open Arabic LLM Leaderboard v1’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen2.5-Math-72B-Instruct, at 73.9%. This view shows only models we track, each at its best.
The newest model with a score here came out in January 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 92.9 elmrc juhaina
- 87.7 mssqpi Waie1
- 85.0 llm-mle ara_mle_pretrained_8b
- 85.0 llm-mle arb_mle_pretrained_8b
- 78.9 silma-ai SILMA-9B-Instruct-v1.0
- 77.1 byroneverson gemma-2-27b-it-abliterated
- 76.3 migtissera Tess-v2.5-Gemma-2-27B-alpha
- 76.2 airev-ai qwen-14b-v2
- 75.8 elmrc juhainaG
- 75.8 elmresearchcenter juhaina
- 73.9
Qwen2.5-Math-72B-Instruct
- 73.7 Slim205 Barka-9b-it-v02
- 73.1 google/gemma-2-27b-it
- 72.6 airev-ai emirati-14b-v3
- 72.5 dnhkng RYS-Gemma-2-27b-it
- 71.6 OpenBuddy openbuddy-deepseek-67b-v18.1-4k
- 71.4 vicgalle CarbonBeagle-11B
- 71.2 MaziyarPanahi calme-2.2-qwen2-72b
- 70.2 elmrc Juhaina28B
- 69.7 vicgalle ConfigurableBeagle-11B
- 69.6 thariqkhalid ara_mle_sft_300_8b
- 69.5 cognitivecomputations WestLake-7B-v2-laser
- 69.1 airev-ai emirati-14b-v2
- 69.0 elmrc Juhaina29B
- 69.0 Sakalti Saka-3.8B
- 68.6 INSAIT-Institute BgGPT-7B-Instruct-v0.2
- 68.3 Qwen/Qwen2.5-Math-72B
- 67.7 Sakalti ultiima-78B-V2
- 67.5 jsfs11 MixtureofMerges-MoE-4x7b-v4
- 67.5 elmrc Juhaina-Instruct-v1
- 67.4 dfurman CalmeRys-78B-Orpo-v0.1
- 67.3 MaziyarPanahi Calme-4x7B-MoE-v0.2
- 67.0 tiiuae/falcon-180B-chat
- 67.0 dnhkng RYS-XLarge-base
- 66.8 Sakalti ultiima-78B
- 66.6 MaziyarPanahi Calme-4x7B-MoE-v0.1
- 66.5 dnhkng RYS-XLarge
- 66.4 microsoft/Phi-3.5-mini-instruct
- 66.1 airev-ai Amal-70b-v5
- 66.1 vicgalle CarbonBeagle-11B-truthy
- 66.0 cognitivecomputations laserxtral
- 66.0 MTSAIR multi_verse_model
- 65.9 allknowingroger MultiverseEx26-7B-slerp
- 65.8 Kukedlc NeuralSynthesis-7B-v0.1
- 65.7 Kquant03 CognitiveFusion2-4x7B-BF16
- 65.7 liminerity M7-7b
- 65.5 Kukedlc NeuralSynthesis-7B-v0.3
- 65.4 Kukedlc NeuralExperiment-7b-MagicCoder-v7.5
- 65.3 automerger YamshadowExperiment28-7B
- 65.2 Kukedlc NeuralSynthesis-7b-v0.4-slerp
- 65.2 01-ai/Yi-1.5-34B-Chat
- 64.6 jondurbin bagel-dpo-34b-v0.2
- 64.4 dfurman Qwen2-72B-Orpo-v0.1
- 64.2 cloudyu Yi-34Bx2-MOE-200K
- 63.9
Qwen2-72B
- 63.8 AALF gemma-2-27b-it-SimPO-37K-100steps
- 63.8 Undi95 MG-FinalMix-72B
- 63.6 ibivibiv multimaster-7b-v6
- 63.5 Weyaxi Nous-Hermes-2-SUS-Chat-34B-Slerp
- 63.5 jsfs11 MixtureofMerges-MoE-4x7b-v5
- 63.5 airev-ai Amal-70b-v4
- 63.4 kevinpro Hydra-LLaMA3-8B-v0.2
- 63.3 MaziyarPanahi calme-2.1-qwen2-72b
- 63.3 MaziyarPanahi Qwen2-72B-Instruct-v0.1
- 63.3 altomek YiSM-34B-0rn
- 63.2 failspy Phi-3-medium-4k-instruct-abliterated-v3
- 63.0 mssqpi ElmGemma2
- 62.8 shadowml BeagSake-7B
- 62.7 vicgalle ConfigurableSOLAR-10.7B
- 62.7 01-ai/Yi-Coder-9B
- 62.5 abacusai Dracarys-72B-Instruct
- 62.5 alpindale magnum-72b-v1
- 62.5 anthracite-org magnum-v1-72b
- 62.4 Sakalti ultiima-125B
- 62.4 CombinHorizon YiSM-blossom5.1-34B-SLERP
- 62.3 mistralai/Codestral-22B-v0.1
- 62.2 zetasepic Qwen2.5-72B-Instruct-abliterated
- 62.1
Qwen2.5-72B
- 62.1 elmrc ElmJuhaina70B
- 62.0 chujiezheng Smaug-34B-v0.1-ExPO
- 62.0 MaziyarPanahi calme-2.1-qwen2.5-72b
- 62.0 Sakalti ultiima-72B
- 61.9 Replete-AI Replete-LLM-V2.5-Qwen-72b
- 61.9 rombodawg Rombos-LLM-V2.5-Qwen-72b
- 61.8 elmrc JuhainaG2
- 61.8 Azure99 blossom-v5.1-34b
- 61.8 sometimesanotion Lamarck-14B-v0.6
- 61.7 abacusai Smaug-34B-v0.1
- 61.7 meraGPT mera-mix-4x7B
- 61.7 fblgit UNA-SimpleSmaug-34b-v1beta
- 61.7 invalid-coder Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp
- 61.6 jeonsworld CarbonVillain-en-10.7B-v4
- 61.6 Danielbrdz Barcenas-14b-Phi-3-medium-ORPO
- 61.5 MaziyarPanahi calme-2.2-qwen2.5-72b
- 61.3
DeepSeek-R1-Distill-Llama-70B
- 61.1 ConvexAI Luminex-34B-v0.2
- 61.1 arcee-ai Arcee-Nova
- 61.0 Sakalti SakaMoe-3x14B-Instruct
- 61.0 Qwen/Qwen2.5-Coder-7B-Instruct
- 60.9 cognitivecomputations dolphin-2.9.1-mixtral-1x22b
- 60.8 abacusai Smaug-Qwen2-72B-Instruct
- 60.8 MaziyarPanahi Topxtral-4x7B-v0.1
- 60.8 kevinpro Hydra-LLaMA3-8B-v0.1
- 60.7 cloudyu TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16
- 60.7 VAGOsolutions SauerkrautLM-Phi-3-medium
- 60.7 shadowml Mixolar-4x7b
- 60.7 zhengr MixTAO-7Bx2-MoE-v8.1
- 60.6 kekmodel StopCarbon-10.7B-v5
- 60.5 gpt2
- 60.5 freewheelin free-solar-evo-v0.11
- 60.5 anthracite-org magnum-v3-34b
- 60.5 ConvexAI Luminex-34B-v0.1
- 60.2 freewheelin free-solar-evo-v0.13
- 60.1 kevin009 llamaRAGdrama
- 60.0 upstage SOLAR-10.7B-Instruct-v1.0
- 60.0 princeton-nlp Mistral-7B-Base-SFT-IPO
- 59.9 riotu-lab ArabianGPT-0.3B-QA
- 59.9 CultriX NeuralMona_MoE-4x7B
- 59.6 openchat openchat-3.6-8b-20240522
- 59.6 cognitivecomputations dolphin-2.9.3-Yi-1.5-34B-32k
- 59.5 AALF gemma-2-27b-it-SimPO-37K
- 59.5
Falcon3-10B-Instruct
- 59.4 freewheelin free-solar-evo-v0.1
- 59.4 sophosympatheia Midnight-Miqu-70B-v1.5
- 59.1 sometimesanotion Qwen2.5-14B-Vimarckoso-v3
- 59.1 nbeerbower gemma2-gutenberg-27B
- 59.0
Falcon3-7B-Instruct
- 59.0 sometimesanotion Lamarck-14B-v0.7
- 58.9 cognitivecomputations dolphin-2.9.1-yi-1.5-34b
- 58.9 failspy Llama-3-70B-Instruct-abliterated-v3
- 58.7 tiiuae/falcon-7b-instruct
- 58.6 01-ai/Yi-Coder-9B-Chat
- 58.4 royallab ZephRP-m7b
- 58.2 Artples L-MChat-Small
- 58.2 arcee-ai Virtuoso-Lite
- 58.0 jondurbin bagel-dpo-34b-v0.5
- 57.9 CausalLM 34b-beta
- 57.8 beowolx CodeNinja-1.0-OpenChat-7B
- 57.6 hotmailuser QwenSlerp2-14B
- 57.4 airev-ai Amal-70b-v2
- 57.4 elmrc JuhainaL2
- 57.3 NLPark Shi-Cis-Kestrel-uncensored
- 57.2 airev-ai Amal-70b-v1.1
- 57.2 tiiuae/Falcon3-1B-Base
- 57.2 saltlux luxia-21.4b-alignment-v1.0
- 57.0 princeton-nlp Mistral-7B-Base-SFT-RDPO
- 57.0 oobabooga CodeBooga-34B-v0.1
- 56.9 01-ai/Yi-1.5-34B-Chat-16K
- 56.8 RubielLabarta LogoS-7Bx2-MoE-13B-v0.2
- 56.6 mlabonne NeuralMonarch-7B
- 56.5 cloudyu Mixtral_34Bx2_MoE_60B
- 56.3 mlabonne AlphaMonarch-7B
- 55.9 Daemontatox Mawared_GS
- 55.8 saltlux luxia-21.4b-alignment-v1.2
- 55.7 dzakwan dzakwan-MoE-4x7b-Beta
- 55.6 mlabonne Beyonder-4x7B-v3
- 55.5 tenyx Llama3-TenyxChat-70B
- 55.4 princeton-nlp Mistral-7B-Base-SFT-DPO
- 55.3 cloudyu Yi-34Bx2-MoE-60B-DPO
- 55.2
phi-3-medium 14B
- 55.2 SeaLLMs SeaLLM-7B-v2
- 55.0 cloudyu Yi-34Bx2-MoE-60B
- 54.8 byroneverson Yi-1.5-34B-Chat-abliterated
- 54.8 anthracite-org magnum-v2-72b
- 54.8 princeton-nlp Llama-3-Base-8B-SFT-SimPO
- 54.7 Mihaiii Llama-3-pruned-45B-Drobeta-Turnu-Severin
- 54.4 abacusai Slerp-CM-mist-dpo
- 54.3 haoranxu ALMA-13B-Pretrain
- 54.3 Daemontatox Llama3.3-70B-CogniLink
- 54.1 airev-ai Jais-Inception-70b-V1.1
- 54.0 inceptionai jais-family-13b-chat
- 53.9 wenbopan Faro-Yi-34B-DPO
- 53.8 haoranxu ALMA-13B-R
- 53.7 xiangxinai Xiangxin-2XL-Chat-1048k-Chinese-Llama3-70B
- 53.7 huihui-ai Qwen2.5-7B-Instruct-abliterated-v2
- 53.7 VAGOsolutions Llama-3-SauerkrautLM-70b-Instruct
- 53.6 mssqpi ALQLora2
- 53.5 MaziyarPanahi calme-2.4-llama3-70b
- 53.5 mmnga Llama-3-70B-japanese-suzume-vector-v0.1
- 53.4 meta-llama/Meta-Llama-3-70B-Instruct
- 53.3 MaziyarPanahi calme-2.2-llama3-70b
- 53.3 MaziyarPanahi Llama-3-70B-Instruct-DPO-v0.2
- 53.3 princeton-nlp Mistral-7B-Base-SFT-SimPO
- 53.2 wenbopan Faro-Yi-9B-DPO
- 53.1 nvidia Llama3-ChatQA-1.5-8B
- 53.0 vicgalle ConfigurableHermes-7B
- 52.8 tanliboy lambda-qwen2.5-14b-dpo-test
- 52.8 Weyaxi Bagel-Hermes-34B-Slerp
- 52.7 Qwen/Qwen1.5-1.8B
- 52.5
Phi-3-medium-128k-instruct
- 52.5 OpenBuddy openbuddy-yi1.5-34b-v21.3-32k
- 52.5 MaziyarPanahi calme-2.3-llama3-70b
- 52.5 airev-ai Amal-75b-v3
- 52.5 riotu-lab ArabianGPT-01B
- 52.3 MaziyarPanahi calme-2.2-llama3.1-70b
- 52.1 byroneverson Yi-1.5-9B-Chat-abliterated
- 52.0 abacusai Smaug-Llama-3-70B-Instruct-32K
- 52.0 Sakalti ultiima-14B
- 52.0 huihui-ai Qwen2.5-32B-Instruct-abliterated
- 51.9 airev-ai qwen-14b-v1
- 51.8 v000000 Qwen2.5-Lumen-14B
- 51.8 NousResearch Hermes-3-Llama-3.1-70B
- 51.8 Replete-AI Replete-LLM-V2.5-Qwen-14b
- 51.8 Qwen/Qwen2.5-14B-Instruct
- 51.7 princeton-nlp Llama-3-Base-8B-SFT-IPO
- 51.6 Nexusflow Athene-70B
- 51.5 haoranxu ALMA-7B-R
- 51.4 Lambent qwen2.5-reinstruct-alternate-lumen-14B
- 51.4 v000000 Qwen2.5-14B-Gutenberg-1e-Delta
- 51.3 recoilme recoilme-gemma-2-9B-v0.4
- 51.1 v000000 Qwen2.5-14B-Gutenberg-Instruct-Slerpeno
- 51.1 dnhkng RYS-Llama3.1-Large
- 51.0 rombodawg Rombos-LLM-V2.6-Nemotron-70b
- 51.0 yunconglong Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
- 50.9 meta-llama/Meta-Llama-3.1-70B-Instruct
- 50.5 VAGOsolutions Llama-3.1-SauerkrautLM-70b-Instruct
- 50.4 nvidia Llama-3.1-Nemotron-70B-Instruct-HF
- 50.4 NousResearch Nous-Hermes-2-SOLAR-10.7B
- 50.3 OpenBuddy openbuddy-zero-56b-v21.2-32k
- 50.3 princeton-nlp Mistral-7B-Instruct-RRHF
- 50.2 jpacifico Chocolatine-14B-Instruct-DPO-v1.2
- 50.2 princeton-nlp Llama-3-Base-8B-SFT-RDPO
- 50.1 abhishek autotrain-llama3-70b-orpo-v1
- 50.1 allknowingroger Ph3della5-14B
- 50.0 wenbopan Faro-Yi-34B
- 50.0 MaziyarPanahi calme-2.3-llama3.1-70b
- 49.9 01-ai/Yi-1.5-34B-32K
- 49.7 jpacifico Chocolatine-14B-Instruct-4k-DPO
- 49.7 Magpie-Align Llama-3-8B-Magpie-Align-v0.3
- 49.6
Falcon-180B
- 49.4 paloalma ECE-TW3-JRGL-V1
- 49.3 byroneverson Yi-1.5-9B-Chat-16K-abliterated
- 49.3 BAAI Gemma2-9B-IT-Simpo-Infinity-Preference
- 49.2 yunconglong MoE_13B_DPO
- 49.1 elmrc JuhainaL
- 49.1 anthracite-org magnum-v3-27b-kto
- 49.0 google/gemma-2-9b-it
- 48.8 UCLA-AGI Gemma-2-9B-It-SPPO-Iter1
- 48.6 Qwen/Qwen1.5-1.8B-Chat
- 48.5 rombodawg Rombos-LLM-V2.6-Qwen-14b
- 48.3 airev-ai Jais-Inception-70b-V1.2
- 48.2 yunconglong DARE_TIES_13B
- 48.0 lightblue suzume-llama-3-8B-multilingual-orpo-borda-top75
- 48.0 failspy llama-3-70B-Instruct-abliterated
- 48.0 lightblue suzume-llama-3-8B-multilingual-orpo-borda-half
- 47.9 vicgalle Configurable-Mistral-7B
- 47.8
Yi-1.5-9B-Chat
- 47.8 princeton-nlp Llama-3-Base-8B-SFT-DPO
- 47.6
Gemma 2 27B
- 47.6
Command R (03-2024)
- 47.6
Qwen2.5-14B-Instruct-1M
- 47.5 UCLA-AGI Gemma-2-9B-It-SPPO-Iter2
- 47.5 princeton-nlp Llama-3-Base-8B-SFT-KTO
- 47.4 shenzhi-wang Llama3-70B-Chinese-Chat
- 47.3 princeton-nlp Llama-3-Instruct-8B-RDPO-v0.2
- 47.3 migtissera Tess-v2.5-Phi-3-medium-128k-14B
- 47.3 Ashmal MBZUAI-oryx
- 47.3 01-ai/Yi-1.5-9B-Chat-16K
- 47.1 airev-ai Jais-Inception-70b-V1.2.2
- 47.0 princeton-nlp Llama-3-Instruct-8B-DPO-v0.2
- 47.0 UCLA-AGI Gemma-2-9B-It-SPPO-Iter3
- 47.0 abacusai Smaug-Llama-3-70B-Instruct
- 46.8 FreedomIntelligence AceGPT-7B-chat
- 46.8 TareksLab Thalassic-Alpha-LLaMa-70B
- 46.7 princeton-nlp Mistral-7B-Instruct-SimPO
- 46.6 Joseph717171 Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
- 46.5 EpistemeAI Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R2
- 46.5
Yi-1.5-34B
- 46.4 paulml ECE-ILAB-Q1
- 46.4 vicgalle Configurable-Yi-1.5-9B-Chat
- 46.1 MTSAIR MultiVerse_70B
- 46.1 airev-ai Jais-Inception-7b-V0.2
- 46.0 EpistemeAI Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code
- 46.0 Omartificial-Intelligence-Space Arabic-llama3.1-16bit-FT
- 46.0 CohereForAI/aya-23-8B
- 45.9 Omartificial-Intelligence-Space al-baka-llama3-8b-experimental
- 45.8 paloalma TW3-JRGL-v2
- 45.7 freewheelin free-evo-qwen72b-v0.8-re
- 45.6 tiiuae/falcon-40b-instruct
- 45.5 SenseLLM ReflectionCoder-DS-33B
- 45.4 davidkim205 Rhea-72b-v0.5
- 45.3 princeton-nlp Llama-3-Instruct-8B-SimPO-v0.2
- 45.2 Ashmal MBZUAI-ORYX-new
- 45.1 chujiezheng Mistral7B-PairRM-SPPO-ExPO
- 45.1
Qwen1.5-14B-Chat
- 44.9 Artples L-MChat-7b
- 44.9 upstage SOLAR-10.7B-v1.0
- 44.9 UCLA-AGI Mistral7B-PairRM-SPPO
- 44.8 UCLA-AGI Mistral7B-PairRM-SPPO-Iter1
- 44.8 princeton-nlp Mistral-7B-Base-SFT-SLiC-HF
- 44.7 RDson WomboCombo-R1-Coder-14B-Preview
- 44.6 princeton-nlp Llama-3-Base-8B-SFT-SLiC-HF
- 44.5 Syed-Hasan-8503 Phi-3-mini-4K-instruct-cpo-simpo
- 44.5 OpenBuddy openbuddy-llama3.1-8b-v22.3-131k
- 44.4 UCLA-AGI Mistral7B-PairRM-SPPO-Iter2
- 44.4 cognitivecomputations dolphin-2.6-mixtral-8x7b
- 44.2 riotu-lab ArabianGPT-03B
- 44.2 TIGER-Lab MAmmoTH2-8B-Plus
- 44.2 migtissera Tess-M-v1.3
- 44.2 01-ai/Yi-9B-200K
- 44.2 jondurbin airoboros-dpo-70b-3.3
- 44.2 openchat openchat-3.5-0106-gemma
- 44.1 inceptionai jais-adapted-13b-chat
- 44.0 cognitivecomputations dolphin-2.9.3-mistral-nemo-12b
- 44.0 FreedomIntelligence AceGPT-13B-chat
- 44.0
Qwen2.5-14B
- 43.8 princeton-nlp Mistral-7B-Instruct-DPO
- 43.8 FreedomIntelligence AceGPT-7B
- 43.7 sajaw llama-2-7b-RandomGPT-5K-ar
- 43.7 lemon-mint gemma-ko-7b-instruct-v0.62
- 43.6 meta-llama/Llama-2-13b-hf
- 43.6 jondurbin airoboros-70b-3.3
- 43.6 princeton-nlp Mistral-7B-Base-SFT-CPO
- 43.5 UCLA-AGI Mistral7B-PairRM-SPPO-Iter3
- 43.5 cstr llama3-8b-spaetzle-v37
- 43.5 elmrc JuhainaG9B
- 43.5 EpistemeAI Fireball-Alpaca-Llama-3.1-8B-Philos-DPO-200
- 43.5 arcee-ai Llama-3.1-SuperNova-Lite
- 43.5 princeton-nlp gemma-2-9b-it-SimPO
- 43.4 MaziyarPanahi Llama-3-8B-Instruct-v0.10
- 43.4 leafspark Llama-3.1-8B-MultiReflection-Instruct
- 43.4 princeton-nlp Llama-3-Base-8B-SFT-ORPO
- 43.3 princeton-nlp Mistral-7B-Instruct-RDPO
- 43.3 migtissera Tess-v2.5.2-Qwen2-72B
- 43.3 meta-llama/Llama-2-70b-hf
- 43.2 abhishek autotrain-llama3-70b-orpo-v2
- 43.2 DeepMount00 Llama-3.1-8b-Ita
- 43.2
Mistral-7B-Instruct-v0.2
- 43.2 EpistemeAI Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1-KTO-beta
- 43.1 EpistemeAI Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-beta
- 43.1 gbueno86 Meta-LLama-3-Cat-Smaug-LLama-70b
- 43.1 mlabonne NeuralDaredevil-8B-abliterated
- 43.1 arcee-ai Virtuoso-Small
- 43.1 cognitivecomputations dolphin-2.9.1-yi-1.5-9b
- 43.0 airev-ai Jais-Inception-7b-V0.1
- 43.0 failspy Meta-Llama-3-70B-Instruct-abliterated-v3.5
- 43.0 Isaak-Carter Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
- 43.0 abacusai Smaug-72B-v0.1
- 43.0 cognitivecomputations dolphin-2.9.1-llama-3-70b
- 43.0 inceptionai jais-family-30b-16k-chat
- 43.0 abacusai Smaug-Mixtral-v0.1
- 42.9 BAAI Infinity-Instruct-3M-0625-Yi-1.5-9B
- 42.9 recoilme Gemma-2-Ataraxy-Gemmasutra-9B-slerp
- 42.9 EpistemeAI2 Fireball-Alpaca-Llama-3.1-8B-Instruct-KTO-beta
- 42.8 freewheelin free-llama3-dpo-v0.2
- 42.8 arcee-ai Llama-Spark
- 42.8 meta-llama/Meta-Llama-3.1-8B-Instruct
- 42.8 ClusterlabAi GemmAr-7B-v1
- 42.6 AXCXEPT EZO-Qwen2.5-72B-Instruct
- 42.6 paloalma Le_Triomphant-ECE-TW3
- 42.6 cognitivecomputations dolphin-2.9.3-llama-3-8b
- 42.6
Aya Expanse 8B
- 42.6 VAGOsolutions Llama-3.1-SauerkrautLM-8b-Instruct
- 42.5 Steelskull L3-MS-Astoria-70b
- 42.5 tanliboy lambda-qwen2.5-32b-dpo-test
- 42.4 openchat openchat-3.5-0106
- 42.4 vicgalle Configurable-Llama-3.1-8B-Instruct
- 42.4 pankajmathur orca_mini_v7_72b
- 42.4 MaziyarPanahi Llama-3-8B-Instruct-v0.9
- 42.4 Qwen/Qwen2.5-Math-7B
- 42.4 princeton-nlp Mistral-7B-Instruct-KTO
- 42.4 inceptionai jais-adapted-70b-chat
- 42.3 bunnycore HyperLlama-3.1-8B
- 42.3 brucethemoose Yi-34B-200K-DARE-merge-v7
- 42.2 cognitivecomputations dolphin-2.9.2-Phi-3-Medium
- 42.2 anthracite-org magnum-v3-9b-customgemma2
- 42.2 mssqpi G3
- 42.2 princeton-nlp Llama-3-Instruct-8B-IPO-v0.2
- 42.2 silma-ai SILMA-9B-Instruct-v0.1
- 42.2 silma-ai SILMA-9B-Instruct-v0.1.0
- 42.2 silma-ai SILMA-9B-Instruct-v0.1.1
- 42.1 RLHFlow LLaMA3-iterative-DPO-final
- 42.1 Orenguteng Llama-3.1-8B-Lexi-Uncensored-V2
- 42.0 lightblue suzume-llama-3-8B-multilingual-orpo-borda-full
- 42.0 mlabonne Daredevil-8B-abliterated
- 42.0 princeton-nlp Llama-3-Instruct-8B-KTO-v0.2
- 41.9
Falcon3-3B-Instruct
- 41.9 BAAI Infinity-Instruct-3M-0613-Mistral-7B
- 41.9 deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- 41.9 cognitivecomputations openchat-3.5-0106-laser
- 41.9 dnhkng RYS-Llama-3.1-8B-Instruct
- 41.9 Magpie-Align Llama-3-8B-Magpie-Align-SFT-v0.3
- 41.9 Orenguteng Llama-3.1-8B-Lexi-Uncensored
- 41.8 wenbopan Faro-Yi-9B
- 41.8 rombodawg Everyone-Coder-4x7b-Base
- 41.8 axolotl-ai-co romulus-mistral-nemo-12b-simpo
- 41.7 cognitivecomputations dolphin-2.9.2-Phi-3-Medium-abliterated
- 41.7 tiiuae/falcon-11B
- 41.7 grimjim Llama-3.1-8B-Instruct-abliterated_via_adapter
- 41.7 SeaLLMs SeaLLM-7B-v2.5
- 41.7 vicgalle Configurable-Hermes-2-Pro-Llama-3-8B
- 41.6 CohereForAI/aya-23-35B
- 41.6 FreedomIntelligence AceGPT-13B
- 41.6 uukuguy zephyr-7b-alpha-dare-0.85
- 41.6 princeton-nlp gemma-2-9b-it-DPO
- 41.6 tiiuae/Falcon3-7B-Base
- 41.5 cognitivecomputations dolphin-2.9.3-mistral-7B-32k
- 41.5
Qwen2.5-Coder (7B)
- 41.5
Falcon3-1B-Instruct
- 41.5 uygarkurt llama-3-merged-linear
- 41.4 Magpie-Align MagpieLM-8B-Chat-v0.1
- 41.4
Gemma 2 9B
- 41.4 recoilme recoilme-gemma-2-9B-v0.2
- 41.4 VAGOsolutions Llama-3-SauerkrautLM-8b-Instruct
- 41.4 princeton-nlp Llama-3-Instruct-8B-RDPO
- 41.3 DeepMount00 Llama-3-8b-Ita
- 41.3 FiditeNemini Unhinged-Qwen2-72B
- 41.3 MaziyarPanahi Llama-3-8B-Instruct-v0.8
- 41.3 princeton-nlp Llama-3-Instruct-8B-DPO
- 41.3 princeton-nlp Llama-3-Instruct-8B-CPO-v0.2
- 41.2 vicgalle Configurable-Janus-7B
- 41.2 jondurbin bagel-8b-v1.0
- 41.1 Isaak-Carter Josiefied-Qwen2.5-7B-Instruct-abliterated
- 41.1 TheDrummer Gemmasutra-9B-v1
- 41.0 princeton-nlp Mistral-7B-Instruct-IPO
- 41.0 amazon MegaBeam-Mistral-7B-300k
- 41.0 Dampfinchen Llama-3.1-8B-Ultra-Instruct
- 41.0 VAGOsolutions SauerkrautLM-Gemma-7b
- 41.0 BAAI Infinity-Instruct-3M-0625-Llama3-8B
- 40.9 migtissera Tess-3-Mistral-Nemo-12B
- 40.9 NotAiLOL Yi-1.5-dolphin-9B
- 40.9 princeton-nlp Llama-3-Base-8B-SFT-RRHF
- 40.9 princeton-nlp Llama-3-Base-8B-SFT
- 40.9 inceptionai jais-adapted-70b
- 40.8 uukuguy speechless-zephyr-code-functionary-7b
- 40.8 airev-ai Jais-Inception-70b
- 40.8 anthracite-org magnum-v3-9b-chatml
- 40.8 618AI dictalm2-it-qa-fine-tune
- 40.7 TIGER-Lab MAmmoTH2-7B-Plus
- 40.7 migtissera Tess-3-Llama-3.1-70B
- 40.7 OpenBuddy openbuddy-qwen2.5llamaify-14b-v23.1-200k
- 40.7 Eurdem Defne-llama3.1-8B
- 40.7 princeton-nlp Llama-3-Instruct-8B-KTO
- 40.7 Replete-AI Replete-LLM-V2.5-Qwen-32b
- 40.7 ValiantLabs Llama3.1-8B-ShiningValiant2
- 40.7 NousResearch Hermes-2-Theta-Llama-3-8B
- 40.7 Qwen/Qwen2.5-32B-Instruct
- 40.6 v000000 L3.1-Niitorm-8B-DPO-t0.0001
- 40.6 meta-llama/Llama-3.2-3B-Instruct
- 40.6 princeton-nlp Llama-3-Base-8B-SFT-CPO
- 40.6 core42 jais-13b-chat
- 40.6 princeton-nlp Llama-3-Instruct-8B-SimPO
- 40.6
Gemma 2B
- 40.6 core42 jais-30b-chat-v1
- 40.6 FreedomIntelligence AceGPT-v2-8B-Chat
- 40.6 inceptionai jais-family-6p7b-chat
- 40.6 princeton-nlp Llama-3-Instruct-8B-ORPO-v0.2
- 40.6 silma-ai SILMA-Kashif-2B-Instruct-v1.0
- 40.5 Sakalti ultiima-32B
- 40.5 Qwen2.5-Coder-14B
- 40.5 uukuguy speechless-code-mistral-7b-v1.0
- 40.5 c4ai-command-r-08-2024
- 40.5 inceptionai jais-adapted-7b-chat
- 40.5 TIGER-Lab MAmmoTH2-8x7B-Plus
- 40.4 cognitivecomputations dolphin-2.9.2-qwen2-72b
- 40.4 BAAI OPI-Llama-3.1-8B-Instruct
- 40.4 Ba2han QwQenSeek-coder
- 40.4 cognitivecomputations dolphin-2.9.1-llama-3-8b
- 40.4 cognitivecomputations Llama-3-8B-Instruct-abliterated-v2
- 40.4 Ali-C137 Ge1H10M-0000
- 40.4 inceptionai jais-family-2p7b-chat
- 40.4 mlabonne ChimeraLlama-3-8B-v2
- 40.4 failspy Smaug-Llama-3-70B-Instruct-abliterated-v3
- 40.4 maldv Qwenstein2.5-32B-Instruct
- 40.4 gbueno86 Meta-LLama-3-Cat-A-LLama-70b
- 40.4 princeton-nlp Llama-3-Instruct-8B-RRHF-v0.2
- 40.4 princeton-nlp Llama-3-Instruct-8B-SLiC-HF-v0.2
- 40.3 princeton-nlp Mistral-7B-Instruct-CPO
- 40.3 huihui-ai Qwen2.5-7B-Instruct-abliterated
- 40.3 inceptionai jais-family-30b-8k-chat
- 40.3 FreedomIntelligence AceGPT-v2-70B
- 40.3 sambanovasystems SambaLingo-Arabic-Chat
- 40.3 01-ai/Yi-1.5-9B-32K
- 40.3 google/gemma-7b-it
- 40.3 grimjim Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
- 40.3 kaist-ai mistral-orpo-capybara-7k
- 40.3 nbeerbower DeepSeek-R1-Qwen-lorablated-32B
- 40.2
Gemma 7B
- 40.2 grimjim Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge
- 40.2
Gemma 1.1 7B IT
- 40.2 BAAI Infinity-Instruct-7M-Gen-Llama3_1-70B
- 40.2
Llama 3.1-70B
- 40.2 GritLM GritLM-8x7B-KTO
- 40.2 ibivibiv llama-3-nectar-dpo-8B
- 40.2 Magpie-Align MagpieLM-8B-SFT-v0.1
- 40.2 qnguyen3 Master-Yi-9B
- 40.2 Daemontatox MawaredT1
- 40.1 EpistemeAI2 Fireball-Llama-3.1-8B-Philos-Relection
- 40.1 tiiuae/Falcon3-10B-Base
- 40.1 nbeerbower mistral-nemo-wissenschaft-12B
- 40.1
Gemma 1.1 2B IT
- 40.1 Kukedlc NeuralLLaMa-3-8b-ORPO-v0.3
- 40.1
Falcon-40B
- 40.1 core42 jais-30b-chat-v3
- 40.1 failspy Codestral-22B-v0.1-abliterated-v3
- 40.1 NLPark AnFeng_v3.1-Avocet
- 40.1 Ali-C137 F1H10M-0000
- 40.1
Falcon-7B
- 40.1 Kukedlc NeuralLLaMa-3-8b-DT-v0.1
- 40.1 migtissera Llama-3-70B-Synthia-v3.5
- 40.1 princeton-nlp Mistral-7B-Base-SFT-KTO
- 40.1 OpenBuddy openbuddy-qwen2.5llamaify-7b-v23.1-200k
- 40.1 migtissera Tess-v2.5-Qwen2-72B
- 40.1 01-ai/Yi-1.5-9B
- 40.1 princeton-nlp Llama-3-Instruct-8B-CPO
- 40.1 terrycraddock Reflection-Llama-3.1-8B
- 40.1 yellowtown 7B-v0.2
- 40.0 maywell Synatra-7B-v0.3-RP
- 40.0 SakanaAI DiscoPOP-zephyr-7b-gemma
- 40.0 kaist-ai janus-rm-7b
- 40.0 GritLM GritLM-8x7B
- 40.0 riotu-lab ArabianGPT-08B-V2
- 40.0 MarinaraSpaghetti NemoReRemix-12B
- 40.0 huihui-ai DeepSeek-R1-Distill-Qwen-32B-abliterated
- 40.0 Ali-C137 L2H10M-0000
- 40.0 kaist-ai janus-dpo-7b
- 40.0 Magpie-Align Llama-3.1-8B-Magpie-Align-SFT-v0.1
- 40.0 meta-llama/Llama-2-7b-hf
- 40.0 princeton-nlp Mistral-7B-Base-SFT-RRHF
- 40.0 Danielbrdz Barcenas-Llama3-8b-ORPO
- 40.0 kaist-ai janus-7b
- 40.0 NTQAI Nxcode-CQ-7B-orpo
- 40.0 princeton-nlp Llama-3-8B-ProLong-64k-Instruct
- 40.0 SenseLLM ReflectionCoder-CL-34B
- 40.0 google/gemma-2b-it
- 40.0 MaziyarPanahi Mistral-7B-Instruct-v0.3
- 40.0 migtissera Tess-2.0-Llama-3-70B
- 40.0 mistralai/Mistral-7B-Instruct-v0.3
- 40.0 utter-project EuroLLM-9B-Instruct
- 40.0 abacusai bigstral-12b-32k
- 39.9 FreedomIntelligence AceGPT-v1.5-13B
- 39.9 princeton-nlp Mistral-7B-Instruct-ORPO
- 39.9 princeton-nlp Mistral-7B-Instruct-SLiC-HF
- 39.9 inceptionai jais-adapted-13b
- 39.9 princeton-nlp Llama-3-8B-ProLong-512k-Instruct
- 39.9 meta-llama/Meta-Llama-3-8B-Instruct
- 39.9 Triangle104 DeepSky-T100
- 39.9
Llama 3.2 1B
- 39.9 ghost-x ghost-8b-beta-1608
- 39.9 mlabonne ChimeraLlama-3-8B-v3
- 39.9 UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter3
- 39.9 2A2I-R L1000MT
- 39.9 2A2I-R L100MT
- 39.9 2A2I-R L200MT
- 39.9 2A2I-R L500MT
- 39.9 SicariusSicariiStuff Qwen2.5-14B_Uncencored
- 39.9 UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter1
- 39.9 dicta-il dictalm2.0-instruct
- 39.9 UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter2
- 39.8 HeshamHaroon llama-3-instruct-slerp-arabic
- 39.8 anthracite-org magnum-v2.5-12b-kto
- 39.8 bigscience bloom-7b1
- 39.8 lightblue suzume-llama-3-8B-multilingual
- 39.8 lightblue suzume-llama-3-8B-multilingual-orpo-borda-top25
- 39.8 OpenBuddy openbuddy-llama3-70b-v21.2-32k
- 39.8 paloalma ECE-TW3-JRGL-V3
- 39.8 princeton-nlp Llama-3-Instruct-8B-IPO
- 39.8 vicgalle Configurable-Llama-3-8B-v0.3
- 39.8 failspy Meta-Llama-3-8B-Instruct-abliterated-v3
- 39.8 FreedomIntelligence AceGPT-v2-32B-Chat
- 39.8 google/recurrentgemma-2b-it
- 39.8 CohereForAI/c4ai-command-r-plus-08-2024
- 39.8 Sakalti Saka-24B
- 39.8
Llama 3.1-8B
- 39.8
DeepSeek-R1-Distill-Qwen-7B
- 39.8 FreedomIntelligence AceGPT-v1.5-13B-Chat
- 39.8 gaverfraxz Meta-Llama-3.1-8B-Instruct-HalfAbliterated-TIES
- 39.8 princeton-nlp Llama-3-Instruct-8B-RRHF
- 39.8 princeton-nlp Llama-3-Instruct-8B-SLiC-HF
- 39.8 v000000 SwallowMaid-8B-L3-SPPO-abliterated
- 39.8 cognitivecomputations dolphin-2.7-mixtral-8x7b
- 39.8 speakleash Bielik-11B-v2.3-Instruct
- 39.8 aws-prototyping MegaBeam-Mistral-7B-512k
- 39.8 ibivibiv llama3-8b-instruct-summary-combined
- 39.7 Delta-Vector Odin-9B
- 39.7 dfurman Llama-3-70B-Orpo-v0.1
- 39.7 recoilme recoilme-gemma-2-9B-v0.3
- 39.7 BAAI Infinity-Instruct-7M-Gen-Llama3_1-8B
- 39.7 migtissera Tess-2.0-Llama-3-70B-v0.2
- 39.7 Nohobby Q2.5-Qwetiapin-32B
- 39.7
Llama 3-70B
- 39.7 abacusai bigyi-15b
- 39.7 ai21labs AI21-Jamba-1.5-Mini
- 39.7 CohereForAI/c4ai-command-r-plus
- 39.7 kaist-ai janus-orpo-7b
- 39.7 tokyotech-llm Llama-3-Swallow-8B-Instruct-v0.1
- 39.7 GritLM GritLM-7B
- 39.7 rombodawg rombos_Replete-Coder-Instruct-8b-Merged
- 39.7
Qwen2.5-32B
- 39.7 core42 jais-30b-v1
- 39.7 core42 jais-30b-v3
- 39.7 inceptionai jais-family-30b-8k
- 39.7 princeton-nlp Llama-3-Instruct-8B-ORPO
- 39.7 sambanovasystems SambaLingo-Arabic-Base-70B
- 39.7 utter-project EuroLLM-9B
- 39.7
Qwen1.5-7B-Chat
- 39.7 SeaLLMs SeaLLMs-v3-7B-Chat
- 39.7 anthracite-org magnum-v4-9b
- 39.7 Qwen/Qwen2.5-7B-Instruct
- 39.6 abacusai Llama-3-Smaug-8B
- 39.6 inceptionai jais-family-1p3b-chat
- 39.6 natong19 Mistral-Nemo-Instruct-2407-abliterated
- 39.6 OpenBuddy openbuddy-yi1.5-34b-v21.6-32k-fp16
- 39.6 Replete-AI Replete-LLM-V2.5-Qwen-7b
- 39.6 Ali-C137 M03H10M-0000
- 39.6 MaziyarPanahi Mistral-7B-v0.3
- 39.6 nyunai nyun-c2-llama3-56B
- 39.6
Mistral 7B v0.3
- 39.6
DeepSeek-R1-Distill-Qwen-14B
- 39.6 inceptionai jais-adapted-7b
- 39.6 Kukedlc NeuralLLaMa-3-8b-ORPO-v0.4
- 39.6 sambanovasystems SambaLingo-Arabic-Base
- 39.6 turboderp Cat-Llama-3-70B-instruct
- 39.6 dfurman Llama-3-8B-Orpo-v0.1
- 39.6 inceptionai jais-family-30b-16k
- 39.6 MaziyarPanahi calme-2.3-qwen2-72b
- 39.6 MaziyarPanahi calme-2.3-qwen2-7b
- 39.6 Qwen/Qwen2.5-3B-Instruct
- 39.6 speakleash Bielik-11B-v2
- 39.6 vicgalle Configurable-Hermes-3-Llama-3.1-8B
- 39.6 maywell Qwen2-7B-Multilingual-RP
- 39.6 MaziyarPanahi calme-2.2-qwen2-7b
- 39.6 MaziyarPanahi calme-2.4-qwen2-7b
- 39.6 prithivMLmods Qwen2.5-32B-DeepSeek-R1-Instruct
- 39.6 RDson CoderO1-DeepSeekR1-Coder-32B-Preview
- 39.6 riotu-lab ArabianGPT-1.5B
- 39.6 GritLM GritLM-7B-KTO
- 39.6 Sakalti Saka-7.6B
- 39.6 sambanovasystems SambaLingo-Arabic-Chat-70B
- 39.6 SicariusSicariiStuff Qwen2.5-14B_Uncensored_Instruct
- 39.6 arcee-ai Arcee-Spark
- 39.6 mlabonne FineLlama-3.1-8B
- 39.6 mlabonne Meta-Llama-3.1-8B-Instruct-abliterated
- 39.6 NaniDAO deepseek-r1-qwen-2.5-32B-ablated
- 39.6 NousResearch Hermes-3-Llama-3.1-8B
- 39.6
Qwen2.5-1.5B
- 39.6 dicta-il dictalm2.0
- 39.6 MohamedRashad Arabic-Orpo-Llama-3-8B-Instruct
- 39.6
Qwen1.5-72B
- 39.5 Ali-C137 PG7BB
- 39.5 Ali-C137 Q2AW1M-0000
- 39.5 Ali-C137 Q2AW1M-0010
- 39.5 Ali-C137 Q2AW1M-0100
- 39.5 Ali-C137 Q2AW1M-1000
- 39.5 Ali-C137 Q2AW1M-1010
- 39.5 Ali-C137 Q2AW1M-1100
- 39.5 Ali-C137 Q2H10M-0000
- 39.5 informatiker Qwen2-7B-Instruct-abliterated
- 39.5 MaziyarPanahi calme-2.5-qwen2-7b
- 39.5 natong19 Qwen2-7B-Instruct-abliterated
- 39.5 prithivMLmods Qwen2.5-14B-DeepSeek-R1-1M
- 39.5
Qwen2-7B-Instruct
- 39.5
Qwen2.5-3B
- 39.5
Qwen2.5-7B
- 39.5 inceptionai jais-family-590m-chat
- 39.5 VAGOsolutions SauerkrautLM-Nemo-12b-Instruct
- 39.5 cognitivecomputations dolphin-2.9.4-llama3.1-8b
- 39.5 FreedomIntelligence AceGPT-v2-70B-Chat
- 39.5 nicoboss DeepSeek-R1-Distill-Qwen-32B-Uncensored
- 39.5 tiiuae/Falcon3-3B-Base
- 39.5
Qwen2-7B
- 39.5 AXCXEPT EZO-Qwen2.5-32B-Instruct
- 39.5 inceptionai jais-family-13b
- 39.5 NousResearch Nous-Hermes-2-Mixtral-8x7B-DPO
- 39.5 Qwen/Qwen2-MoE-57B-A14B
- 39.5
Qwen1.5-14B
- 39.5 abacusai Liberated-Qwen1.5-14B
- 39.5 AIDC-AI Marco-LLM-AR
- 39.5 Ali-C137 Q2AW1M-0001
- 39.5 Ali-C137 Q2AW1M-0111
- 39.5 Ali-C137 Q2AW1M-1001
- 39.5 Ali-C137 Q2AW1M-1111
- 39.5 asas-ai AceGPT-v2-32B
- 39.5 BAAI Infinity-Instruct-3M-0625-Qwen2-7B
- 39.5 cognitivecomputations dolphin-2.9.2-qwen2-7b
- 39.5 core42 jais-13b
- 39.5 Cran-May T.E-8.1
- 39.5 FreedomIntelligence AceGPT-v2-32B
- 39.5 HeshamHaroon Testv1
- 39.5 hotmailuser Deeepseek-QwenSlerp4-32B
- 39.5 inceptionai jais-family-1p3b
- 39.5 inceptionai jais-family-2p7b
- 39.5 inceptionai jais-family-590m
- 39.5 inceptionai jais-family-6p7b
- 39.5 macadeliccc Samantha-Qwen-2-7B
- 39.5 MaziyarPanahi calme-2.1-qwen2-7b
- 39.5 MaziyarPanahi calme-2.6-qwen2-7b
- 39.5 MaziyarPanahi calme-2.7-qwen2-7b
- 39.5 MBZUAI MobiLlama-1B
- 39.5 nitky RoguePlanet-DeepSeek-R1-Qwen-32B
- 39.5 oddadmix Arabic-Qwen2.5-3B
- 39.5 oddadmix Arabic-Qwen2.5-3B-v2
- 39.5 oddadmix Arabic-Qwen2.5-3B-v2.1
- 39.5 OpenBuddy openbuddy-qwen1.5-32b-v21.1-32k
- 39.5 OpenBuddy openbuddy-qwen1.5-32b-v21.2-32k
- 39.5 Orion-zhen Qwen2.5-7B-Instruct-Uncensored
- 39.5 paloalma ECE-TW3-JRGL-V2
- 39.5 Qwen/Qwen1.5-0.5B
- 39.5 Qwen/Qwen1.5-0.5B-Chat
- 39.5 Qwen/Qwen1.5-32B-Chat
- 39.5 Qwen/Qwen1.5-4B
- 39.5 Qwen/Qwen1.5-MoE-A2.7B
- 39.5 Qwen/Qwen1.5-MoE-A2.7B-Chat
- 39.5 Qwen/Qwen2-MoE-57B-A14B-Instruct
- 39.5 Qwen/Qwen2.5-1.5B-Instruct
- 39.5 Qwen/Qwen2.5-Math-7B-Instruct
- 39.5 Sakalti Saka-1.5B
- 39.5 TeetouchQQ model_mergev2
- 39.5 VAGOsolutions SauerkrautLM-Qwen-32b
- 39.5 vilm Quyen-Pro-Max-v0.1
- 39.5 Weyaxi Einstein-v7-Qwen2-7B
- 39.5
Qwen1.5-32B
- 39.5
Qwen1.5-4B-Chat
- 39.5
Qwen1.5-110B
- 39.5
Qwen2-0.5B
- 39.5
Qwen2-0.5B-Instruct
- 39.5
Qwen2-1.5B
- 39.5
Qwen2-1.5B-Instruct
- 39.5
Qwen2.5-0.5B
- 39.5 Qwen2.5-Coder-14B-Instruct
- 39.5 ai21labs Jamba-v0.1
- 39.5 google/recurrentgemma-2b
- 39.5 Slim205 Barka-2b-it
- 39.5 Qwen/Qwen1.5-110B-Chat
- 39.5
Qwen1.5-7B
- 39.5 Ali-C137 Q15H10M-0000
- 39.5 paloalma ECE-TW3-JRGL-V4
- 39.4 Ali-C137 L3H10M-0000
- 39.4
Llama 3-8B
- 39.4 princeton-nlp Llama-3-8B-ProLong-64k-Base
- 39.4 rombodawg rombos_Replete-Coder-Llama3-8B
- 39.2 unsloth llama-3-8b-bnb-4bit
- 1 elmrc juhaina fine-tuned on domain-specific datasets, bfloat16 92.9%
- 2 mssqpi Waie1 chat models, bfloat16 87.7%
- 3 llm-mle ara_mle_pretrained_8b , bfloat16 85%
- 4 llm-mle arb_mle_pretrained_8b pretrained, bfloat16 85%
- 5 silma-ai SILMA-9B-Instruct-v1.0 chat models, bfloat16 78.9%
- 6 byroneverson gemma-2-27b-it-abliterated fine-tuned on domain-specific datasets, bfloat16 77.1%
- 7 migtissera Tess-v2.5-Gemma-2-27B-alpha fine-tuned on domain-specific datasets, bfloat16 76.3%
- 8 airev-ai qwen-14b-v2 , float16 76.2%
- 9 elmrc juhainaG fine-tuned on domain-specific datasets, bfloat16 75.8%
- 10 elmresearchcenter juhaina fine-tuned on domain-specific datasets, bfloat16 75.8%
- 11
Qwen2.5-Math-72B-Instruct fine-tuned on domain-specific datasets, bfloat16 73.9%
- 12 Slim205 Barka-9b-it-v02 fine-tuned on domain-specific datasets, bfloat16 73.7%
- 13 google/gemma-2-27b-it chat models, bfloat16 73.1%
- 14 airev-ai emirati-14b-v3 fine-tuned on domain-specific datasets, bfloat16 72.6%
- 15 dnhkng RYS-Gemma-2-27b-it fine-tuned on domain-specific datasets, bfloat16 72.5%
- 16 OpenBuddy openbuddy-deepseek-67b-v18.1-4k chat models, bfloat16 71.6%
- 17 vicgalle CarbonBeagle-11B base merges and moerges, float16 71.4%
- 18 MaziyarPanahi calme-2.2-qwen2-72b chat models, bfloat16 71.2%
- 19 elmrc Juhaina28B , ? 70.2%
- 20 vicgalle ConfigurableBeagle-11B chat models, float16 69.7%
- 21 thariqkhalid ara_mle_sft_300_8b , bfloat16 69.6%
- 22 cognitivecomputations WestLake-7B-v2-laser , float16 69.5%
- 23 airev-ai emirati-14b-v2 fine-tuned on domain-specific datasets, bfloat16 69.1%
- 24 elmrc Juhaina29B chat models, bfloat16 69%
- 25 Sakalti Saka-3.8B base merges and moerges, float16 69%
- 26 INSAIT-Institute BgGPT-7B-Instruct-v0.2 pretrained, bfloat16 68.6%
- 27 Qwen/Qwen2.5-Math-72B pretrained, bfloat16 68.3%
- 28 Sakalti ultiima-78B-V2 base merges and moerges, float16 67.7%
- 29 jsfs11 MixtureofMerges-MoE-4x7b-v4 base merges and moerges, bfloat16 67.5%
- 30 elmrc Juhaina-Instruct-v1 chat models, bfloat16 67.5%
- 31 dfurman CalmeRys-78B-Orpo-v0.1 chat models, bfloat16 67.4%
- 32 MaziyarPanahi Calme-4x7B-MoE-v0.2 base merges and moerges, bfloat16 67.3%
- 33 tiiuae/falcon-180B-chat fine-tuned on domain-specific datasets, bfloat16 67%
- 34 dnhkng RYS-XLarge-base fine-tuned on domain-specific datasets, bfloat16 67%
- 35 Sakalti ultiima-78B fine-tuned on domain-specific datasets, float16 66.8%
- 36 MaziyarPanahi Calme-4x7B-MoE-v0.1 base merges and moerges, bfloat16 66.6%
- 37 dnhkng RYS-XLarge chat models, bfloat16 66.5%
- 38 microsoft/Phi-3.5-mini-instruct , bfloat16 66.4%
- 39 airev-ai Amal-70b-v5 , float16 66.1%
- 40 vicgalle CarbonBeagle-11B-truthy fine-tuned on domain-specific datasets, float16 66.1%
- 41 cognitivecomputations laserxtral fine-tuned on domain-specific datasets, bfloat16 66%
- 42 MTSAIR multi_verse_model fine-tuned on domain-specific datasets, bfloat16 66%
- 43 allknowingroger MultiverseEx26-7B-slerp base merges and moerges, bfloat16 65.9%
- 44 Kukedlc NeuralSynthesis-7B-v0.1 base merges and moerges, bfloat16 65.8%
- 45 Kquant03 CognitiveFusion2-4x7B-BF16 base merges and moerges, bfloat16 65.7%
- 46 liminerity M7-7b base merges and moerges, bfloat16 65.7%
- 47 Kukedlc NeuralSynthesis-7B-v0.3 base merges and moerges, bfloat16 65.5%
- 48 Kukedlc NeuralExperiment-7b-MagicCoder-v7.5 fine-tuned on domain-specific datasets, float16 65.4%
- 49 automerger YamshadowExperiment28-7B base merges and moerges, bfloat16 65.3%
- 50 Kukedlc NeuralSynthesis-7b-v0.4-slerp base merges and moerges, bfloat16 65.2%
- 51 01-ai/Yi-1.5-34B-Chat chat models, bfloat16 65.2%
- 52 jondurbin bagel-dpo-34b-v0.2 chat models, bfloat16 64.6%
- 53 dfurman Qwen2-72B-Orpo-v0.1 chat models, bfloat16 64.4%
- 54 cloudyu Yi-34Bx2-MOE-200K base merges and moerges, bfloat16 64.2%
- 55
Qwen2-72B chat models, bfloat16 63.9%
- 56 AALF gemma-2-27b-it-SimPO-37K-100steps chat models, bfloat16 63.8%
- 57 Undi95 MG-FinalMix-72B fine-tuned on domain-specific datasets, bfloat16 63.8%
- 58 ibivibiv multimaster-7b-v6 , ? 63.6%
- 59 Weyaxi Nous-Hermes-2-SUS-Chat-34B-Slerp base merges and moerges, bfloat16 63.5%
- 60 jsfs11 MixtureofMerges-MoE-4x7b-v5 base merges and moerges, bfloat16 63.5%
- 61 airev-ai Amal-70b-v4 , float16 63.5%
- 62 kevinpro Hydra-LLaMA3-8B-v0.2 , ? 63.4%
- 63 MaziyarPanahi calme-2.1-qwen2-72b fine-tuned on domain-specific datasets, bfloat16 63.3%
- 64 MaziyarPanahi Qwen2-72B-Instruct-v0.1 chat models, bfloat16 63.3%
- 65 altomek YiSM-34B-0rn base merges and moerges, float16 63.3%
- 66 failspy Phi-3-medium-4k-instruct-abliterated-v3 fine-tuned on domain-specific datasets, bfloat16 63.2%
- 67 mssqpi ElmGemma2 chat models, bfloat16 63%
- 68 shadowml BeagSake-7B base merges and moerges, bfloat16 62.8%
- 69 vicgalle ConfigurableSOLAR-10.7B chat models, float16 62.7%
- 70 01-ai/Yi-Coder-9B pretrained, bfloat16 62.7%
- 71 abacusai Dracarys-72B-Instruct fine-tuned on domain-specific datasets, bfloat16 62.5%
- 72 alpindale magnum-72b-v1 fine-tuned on domain-specific datasets, bfloat16 62.5%
- 73 anthracite-org magnum-v1-72b fine-tuned on domain-specific datasets, bfloat16 62.5%
- 74 Sakalti ultiima-125B fine-tuned on domain-specific datasets, float16 62.4%
- 75 CombinHorizon YiSM-blossom5.1-34B-SLERP base merges and moerges, bfloat16 62.4%
- 76 mistralai/Codestral-22B-v0.1 fine-tuned on domain-specific datasets, bfloat16 62.3%
- 77 zetasepic Qwen2.5-72B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 62.2%
- 78
Qwen2.5-72B chat models, bfloat16 62.1%
- 79 elmrc ElmJuhaina70B chat models, bfloat16 62.1%
- 80 chujiezheng Smaug-34B-v0.1-ExPO fine-tuned on domain-specific datasets, bfloat16 62%
- 81 MaziyarPanahi calme-2.1-qwen2.5-72b chat models, bfloat16 62%
- 82 Sakalti ultiima-72B fine-tuned on domain-specific datasets, float16 62%
- 83 Replete-AI Replete-LLM-V2.5-Qwen-72b fine-tuned on domain-specific datasets, bfloat16 61.9%
- 84 rombodawg Rombos-LLM-V2.5-Qwen-72b base merges and moerges, bfloat16 61.9%
- 85 elmrc JuhainaG2 chat models, bfloat16 61.8%
- 86 Azure99 blossom-v5.1-34b chat models, bfloat16 61.8%
- 87 sometimesanotion Lamarck-14B-v0.6 base merges and moerges, bfloat16 61.8%
- 88 abacusai Smaug-34B-v0.1 chat models, bfloat16 61.7%
- 89 meraGPT mera-mix-4x7B fine-tuned on domain-specific datasets, bfloat16 61.7%
- 90 fblgit UNA-SimpleSmaug-34b-v1beta base merges and moerges, bfloat16 61.7%
- 91 invalid-coder Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp base merges and moerges, float16 61.7%
- 92 jeonsworld CarbonVillain-en-10.7B-v4 base merges and moerges, float16 61.6%
- 93 Danielbrdz Barcenas-14b-Phi-3-medium-ORPO chat models, float16 61.6%
- 94 MaziyarPanahi calme-2.2-qwen2.5-72b chat models, bfloat16 61.5%
- 95
DeepSeek-R1-Distill-Llama-70B fine-tuned on domain-specific datasets, bfloat16 61.3%
- 96 ConvexAI Luminex-34B-v0.2 , bfloat16 61.1%
- 97 arcee-ai Arcee-Nova chat models, bfloat16 61.1%
- 98 Sakalti SakaMoe-3x14B-Instruct fine-tuned on domain-specific datasets, float16 61%
- 99 Qwen/Qwen2.5-Coder-7B-Instruct fine-tuned on domain-specific datasets, bfloat16 61%
- 100 cognitivecomputations dolphin-2.9.1-mixtral-1x22b fine-tuned on domain-specific datasets, bfloat16 60.9%
- 101 abacusai Smaug-Qwen2-72B-Instruct chat models, bfloat16 60.8%
- 102 MaziyarPanahi Topxtral-4x7B-v0.1 fine-tuned on domain-specific datasets, bfloat16 60.8%
- 103 kevinpro Hydra-LLaMA3-8B-v0.1 , ? 60.8%
- 104 cloudyu TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 chat models, bfloat16 60.7%
- 105 VAGOsolutions SauerkrautLM-Phi-3-medium chat models, bfloat16 60.7%
- 106 shadowml Mixolar-4x7b base merges and moerges, float16 60.7%
- 107 zhengr MixTAO-7Bx2-MoE-v8.1 base merges and moerges, bfloat16 60.7%
- 108 kekmodel StopCarbon-10.7B-v5 base merges and moerges, float16 60.6%
- 109 gpt2 , GPTQ 60.5%
- 110 freewheelin free-solar-evo-v0.11 fine-tuned on domain-specific datasets, float16 60.5%
- 111 anthracite-org magnum-v3-34b chat models, bfloat16 60.5%
- 112 ConvexAI Luminex-34B-v0.1 , bfloat16 60.5%
- 113 freewheelin free-solar-evo-v0.13 fine-tuned on domain-specific datasets, float16 60.2%
- 114 kevin009 llamaRAGdrama chat models, float16 60.1%
- 115 upstage SOLAR-10.7B-Instruct-v1.0 fine-tuned on domain-specific datasets, float16 60%
- 116 princeton-nlp Mistral-7B-Base-SFT-IPO chat models, bfloat16 60%
- 117 riotu-lab ArabianGPT-0.3B-QA , ? 59.9%
- 118 CultriX NeuralMona_MoE-4x7B base merges and moerges, bfloat16 59.9%
- 119 openchat openchat-3.6-8b-20240522 chat models, bfloat16 59.6%
- 120 cognitivecomputations dolphin-2.9.3-Yi-1.5-34B-32k chat models, bfloat16 59.6%
- 121 AALF gemma-2-27b-it-SimPO-37K chat models, bfloat16 59.5%
- 122
Falcon3-10B-Instruct chat models, bfloat16 59.5%
- 123 freewheelin free-solar-evo-v0.1 fine-tuned on domain-specific datasets, float16 59.4%
- 124 sophosympatheia Midnight-Miqu-70B-v1.5 base merges and moerges, float16 59.4%
- 125 sometimesanotion Qwen2.5-14B-Vimarckoso-v3 base merges and moerges, bfloat16 59.1%
- 126 nbeerbower gemma2-gutenberg-27B chat models, bfloat16 59.1%
- 127
Falcon3-7B-Instruct chat models, bfloat16 59%
- 128 sometimesanotion Lamarck-14B-v0.7 chat models, bfloat16 59%
- 129 cognitivecomputations dolphin-2.9.1-yi-1.5-34b fine-tuned on domain-specific datasets, bfloat16 58.9%
- 130 failspy Llama-3-70B-Instruct-abliterated-v3 fine-tuned on domain-specific datasets, bfloat16 58.9%
- 131 tiiuae/falcon-7b-instruct fine-tuned on domain-specific datasets, bfloat16 58.7%
- 132 01-ai/Yi-Coder-9B-Chat fine-tuned on domain-specific datasets, bfloat16 58.6%
- 133 royallab ZephRP-m7b base merges and moerges, bfloat16 58.4%
- 134 Artples L-MChat-Small base merges and moerges, bfloat16 58.2%
- 135 arcee-ai Virtuoso-Lite chat models, bfloat16 58.2%
- 136 jondurbin bagel-dpo-34b-v0.5 chat models, bfloat16 58%
- 137 CausalLM 34b-beta fine-tuned on domain-specific datasets, bfloat16 57.9%
- 138 beowolx CodeNinja-1.0-OpenChat-7B fine-tuned on domain-specific datasets, bfloat16 57.8%
- 139 hotmailuser QwenSlerp2-14B base merges and moerges, bfloat16 57.6%
- 140 airev-ai Amal-70b-v2 fine-tuned on domain-specific datasets, float16 57.4%
- 141 elmrc JuhainaL2 chat models, bfloat16 57.4%
- 142 NLPark Shi-Cis-Kestrel-uncensored chat models, bfloat16 57.3%
- 143 airev-ai Amal-70b-v1.1 , float16 57.2%
- 144 tiiuae/Falcon3-1B-Base pretrained, bfloat16 57.2%
- 145 saltlux luxia-21.4b-alignment-v1.0 chat models, bfloat16 57.2%
- 146 princeton-nlp Mistral-7B-Base-SFT-RDPO chat models, bfloat16 57%
- 147 oobabooga CodeBooga-34B-v0.1 fine-tuned on domain-specific datasets, float16 57%
- 148 01-ai/Yi-1.5-34B-Chat-16K fine-tuned on domain-specific datasets, bfloat16 56.9%
- 149 RubielLabarta LogoS-7Bx2-MoE-13B-v0.2 base merges and moerges, bfloat16 56.8%
- 150 mlabonne NeuralMonarch-7B chat models, float16 56.6%
- 151 cloudyu Mixtral_34Bx2_MoE_60B base merges and moerges, bfloat16 56.5%
- 152 mlabonne AlphaMonarch-7B chat models, float16 56.3%
- 153 Daemontatox Mawared_GS fine-tuned on domain-specific datasets, bfloat16 55.9%
- 154 saltlux luxia-21.4b-alignment-v1.2 chat models, bfloat16 55.8%
- 155 dzakwan dzakwan-MoE-4x7b-Beta fine-tuned on domain-specific datasets, float16 55.7%
- 156 mlabonne Beyonder-4x7B-v3 base merges and moerges, float16 55.6%
- 157 tenyx Llama3-TenyxChat-70B chat models, bfloat16 55.5%
- 158 princeton-nlp Mistral-7B-Base-SFT-DPO chat models, bfloat16 55.4%
- 159 cloudyu Yi-34Bx2-MoE-60B-DPO chat models, bfloat16 55.3%
- 160
phi-3-medium 14B chat models, bfloat16 55.2%
- 161 SeaLLMs SeaLLM-7B-v2 fine-tuned on domain-specific datasets, bfloat16 55.2%
- 162 cloudyu Yi-34Bx2-MoE-60B base merges and moerges, bfloat16 55%
- 163 byroneverson Yi-1.5-34B-Chat-abliterated fine-tuned on domain-specific datasets, bfloat16 54.8%
- 164 anthracite-org magnum-v2-72b chat models, bfloat16 54.8%
- 165 princeton-nlp Llama-3-Base-8B-SFT-SimPO chat models, bfloat16 54.8%
- 166 Mihaiii Llama-3-pruned-45B-Drobeta-Turnu-Severin , bfloat16 54.7%
- 167 abacusai Slerp-CM-mist-dpo chat models, float16 54.4%
- 168 haoranxu ALMA-13B-Pretrain , ? 54.3%
- 169 Daemontatox Llama3.3-70B-CogniLink fine-tuned on domain-specific datasets, bfloat16 54.3%
- 170 airev-ai Jais-Inception-70b-V1.1 chat models, bfloat16 54.1%
- 171 inceptionai jais-family-13b-chat chat models, float16 54%
- 172 wenbopan Faro-Yi-34B-DPO chat models, bfloat16 53.9%
- 173 haoranxu ALMA-13B-R chat models, float16 53.8%
- 174 xiangxinai Xiangxin-2XL-Chat-1048k-Chinese-Llama3-70B chat models, float16 53.7%
- 175 huihui-ai Qwen2.5-7B-Instruct-abliterated-v2 fine-tuned on domain-specific datasets, bfloat16 53.7%
- 176 VAGOsolutions Llama-3-SauerkrautLM-70b-Instruct chat models, bfloat16 53.7%
- 177 mssqpi ALQLora2 , ? 53.6%
- 178 MaziyarPanahi calme-2.4-llama3-70b chat models, bfloat16 53.5%
- 179 mmnga Llama-3-70B-japanese-suzume-vector-v0.1 fine-tuned on domain-specific datasets, bfloat16 53.5%
- 180 meta-llama/Meta-Llama-3-70B-Instruct chat models, bfloat16 53.4%
- 181 MaziyarPanahi calme-2.2-llama3-70b chat models, bfloat16 53.3%
- 182 MaziyarPanahi Llama-3-70B-Instruct-DPO-v0.2 chat models, bfloat16 53.3%
- 183 princeton-nlp Mistral-7B-Base-SFT-SimPO chat models, bfloat16 53.3%
- 184 wenbopan Faro-Yi-9B-DPO , bfloat16 53.2%
- 185 nvidia Llama3-ChatQA-1.5-8B chat models, float16 53.1%
- 186 vicgalle ConfigurableHermes-7B chat models, float16 53%
- 187 tanliboy lambda-qwen2.5-14b-dpo-test chat models, bfloat16 52.8%
- 188 Weyaxi Bagel-Hermes-34B-Slerp base merges and moerges, bfloat16 52.8%
- 189 Qwen/Qwen1.5-1.8B pretrained, bfloat16 52.7%
- 190
Phi-3-medium-128k-instruct chat models, bfloat16 52.5%
- 191 OpenBuddy openbuddy-yi1.5-34b-v21.3-32k chat models, bfloat16 52.5%
- 192 MaziyarPanahi calme-2.3-llama3-70b chat models, bfloat16 52.5%
- 193 airev-ai Amal-75b-v3 , float16 52.5%
- 194 riotu-lab ArabianGPT-01B , ? 52.5%
- 195 MaziyarPanahi calme-2.2-llama3.1-70b chat models, bfloat16 52.3%
- 196 byroneverson Yi-1.5-9B-Chat-abliterated fine-tuned on domain-specific datasets, bfloat16 52.1%
- 197 abacusai Smaug-Llama-3-70B-Instruct-32K chat models, bfloat16 52%
- 198 Sakalti ultiima-14B base merges and moerges, float16 52%
- 199 huihui-ai Qwen2.5-32B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 52%
- 200 airev-ai qwen-14b-v1 , float16 51.9%
- 201 v000000 Qwen2.5-Lumen-14B chat models, bfloat16 51.8%
- 202 NousResearch Hermes-3-Llama-3.1-70B chat models, bfloat16 51.8%
- 203 Replete-AI Replete-LLM-V2.5-Qwen-14b fine-tuned on domain-specific datasets, bfloat16 51.8%
- 204 Qwen/Qwen2.5-14B-Instruct chat models, bfloat16 51.8%
- 205 princeton-nlp Llama-3-Base-8B-SFT-IPO chat models, bfloat16 51.7%
- 206 Nexusflow Athene-70B , bfloat16 51.6%
- 207 haoranxu ALMA-7B-R , float16 51.5%
- 208 Lambent qwen2.5-reinstruct-alternate-lumen-14B base merges and moerges, bfloat16 51.4%
- 209 v000000 Qwen2.5-14B-Gutenberg-1e-Delta chat models, bfloat16 51.4%
- 210 recoilme recoilme-gemma-2-9B-v0.4 fine-tuned on domain-specific datasets, bfloat16 51.3%
- 211 v000000 Qwen2.5-14B-Gutenberg-Instruct-Slerpeno base merges and moerges, bfloat16 51.1%
- 212 dnhkng RYS-Llama3.1-Large fine-tuned on domain-specific datasets, bfloat16 51.1%
- 213 rombodawg Rombos-LLM-V2.6-Nemotron-70b base merges and moerges, bfloat16 51%
- 214 yunconglong Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B chat models, bfloat16 51%
- 215 meta-llama/Meta-Llama-3.1-70B-Instruct chat models, bfloat16 50.9%
- 216 VAGOsolutions Llama-3.1-SauerkrautLM-70b-Instruct fine-tuned on domain-specific datasets, bfloat16 50.5%
- 217 nvidia Llama-3.1-Nemotron-70B-Instruct-HF chat models, bfloat16 50.4%
- 218 NousResearch Nous-Hermes-2-SOLAR-10.7B fine-tuned on domain-specific datasets, bfloat16 50.4%
- 219 OpenBuddy openbuddy-zero-56b-v21.2-32k chat models, bfloat16 50.3%
- 220 princeton-nlp Mistral-7B-Instruct-RRHF chat models, bfloat16 50.3%
- 221 jpacifico Chocolatine-14B-Instruct-DPO-v1.2 chat models, float16 50.2%
- 222 princeton-nlp Llama-3-Base-8B-SFT-RDPO chat models, bfloat16 50.2%
- 223 abhishek autotrain-llama3-70b-orpo-v1 chat models, float16 50.1%
- 224 allknowingroger Ph3della5-14B base merges and moerges, float16 50.1%
- 225 wenbopan Faro-Yi-34B chat models, bfloat16 50%
- 226 MaziyarPanahi calme-2.3-llama3.1-70b chat models, bfloat16 50%
- 227 01-ai/Yi-1.5-34B-32K pretrained, bfloat16 49.9%
- 228 jpacifico Chocolatine-14B-Instruct-4k-DPO chat models, float16 49.7%
- 229 Magpie-Align Llama-3-8B-Magpie-Align-v0.3 chat models, bfloat16 49.7%
- 230
Falcon-180B pretrained, bfloat16 49.6%
- 231 paloalma ECE-TW3-JRGL-V1 base merges and moerges, float16 49.4%
- 232 byroneverson Yi-1.5-9B-Chat-16K-abliterated fine-tuned on domain-specific datasets, bfloat16 49.3%
- 233 BAAI Gemma2-9B-IT-Simpo-Infinity-Preference chat models, bfloat16 49.3%
- 234 yunconglong MoE_13B_DPO chat models, bfloat16 49.2%
- 235 elmrc JuhainaL chat models, bfloat16 49.1%
- 236 anthracite-org magnum-v3-27b-kto , ? 49.1%
- 237 google/gemma-2-9b-it chat models, bfloat16 49%
- 238 UCLA-AGI Gemma-2-9B-It-SPPO-Iter1 chat models, bfloat16 48.8%
- 239 Qwen/Qwen1.5-1.8B-Chat pretrained, bfloat16 48.6%
- 240 rombodawg Rombos-LLM-V2.6-Qwen-14b fine-tuned on domain-specific datasets, bfloat16 48.5%
- 241 airev-ai Jais-Inception-70b-V1.2 , float16 48.3%
- 242 yunconglong DARE_TIES_13B base merges and moerges, bfloat16 48.2%
- 243 lightblue suzume-llama-3-8B-multilingual-orpo-borda-top75 chat models, bfloat16 48%
- 244 failspy llama-3-70B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 48%
- 245 lightblue suzume-llama-3-8B-multilingual-orpo-borda-half chat models, bfloat16 48%
- 246 vicgalle Configurable-Mistral-7B chat models, float16 47.9%
- 247
Yi-1.5-9B-Chat chat models, bfloat16 47.8%
- 248 princeton-nlp Llama-3-Base-8B-SFT-DPO chat models, bfloat16 47.8%
- 249
Gemma 2 27B , ? 47.6%
- 250
Command R (03-2024) fine-tuned on domain-specific datasets, float16 47.6%
- 251
Qwen2.5-14B-Instruct-1M chat models, bfloat16 47.6%
- 252 UCLA-AGI Gemma-2-9B-It-SPPO-Iter2 chat models, bfloat16 47.5%
- 253 princeton-nlp Llama-3-Base-8B-SFT-KTO chat models, bfloat16 47.5%
- 254 shenzhi-wang Llama3-70B-Chinese-Chat chat models, bfloat16 47.4%
- 255 princeton-nlp Llama-3-Instruct-8B-RDPO-v0.2 chat models, bfloat16 47.3%
- 256 migtissera Tess-v2.5-Phi-3-medium-128k-14B fine-tuned on domain-specific datasets, bfloat16 47.3%
- 257 Ashmal MBZUAI-oryx fine-tuned on domain-specific datasets, float16 47.3%
- 258 01-ai/Yi-1.5-9B-Chat-16K fine-tuned on domain-specific datasets, bfloat16 47.3%
- 259 airev-ai Jais-Inception-70b-V1.2.2 , float16 47.1%
- 260 princeton-nlp Llama-3-Instruct-8B-DPO-v0.2 chat models, bfloat16 47%
- 261 UCLA-AGI Gemma-2-9B-It-SPPO-Iter3 chat models, bfloat16 47%
- 262 abacusai Smaug-Llama-3-70B-Instruct chat models, bfloat16 47%
- 263 FreedomIntelligence AceGPT-7B-chat chat models, float16 46.8%
- 264 TareksLab Thalassic-Alpha-LLaMa-70B base merges and moerges, bfloat16 46.8%
- 265 princeton-nlp Mistral-7B-Instruct-SimPO chat models, bfloat16 46.7%
- 266 Joseph717171 Llama-3.1-SuperNova-8B-Lite_TIES_with_Base base merges and moerges, bfloat16 46.6%
- 267 EpistemeAI Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R2 fine-tuned on domain-specific datasets, float16 46.5%
- 268
Yi-1.5-34B pretrained, bfloat16 46.5%
- 269 paulml ECE-ILAB-Q1 base merges and moerges, bfloat16 46.4%
- 270 vicgalle Configurable-Yi-1.5-9B-Chat chat models, float16 46.4%
- 271 MTSAIR MultiVerse_70B fine-tuned on domain-specific datasets, bfloat16 46.1%
- 272 airev-ai Jais-Inception-7b-V0.2 chat models, bfloat16 46.1%
- 273 EpistemeAI Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code fine-tuned on domain-specific datasets, float16 46%
- 274 Omartificial-Intelligence-Space Arabic-llama3.1-16bit-FT , bfloat16 46%
- 275 CohereForAI/aya-23-8B fine-tuned on domain-specific datasets, float16 46%
- 276 Omartificial-Intelligence-Space al-baka-llama3-8b-experimental fine-tuned on domain-specific datasets, float16 45.9%
- 277 paloalma TW3-JRGL-v2 base merges and moerges, bfloat16 45.8%
- 278 freewheelin free-evo-qwen72b-v0.8-re fine-tuned on domain-specific datasets, float16 45.7%
- 279 tiiuae/falcon-40b-instruct fine-tuned on domain-specific datasets, bfloat16 45.6%
- 280 SenseLLM ReflectionCoder-DS-33B chat models, bfloat16 45.5%
- 281 davidkim205 Rhea-72b-v0.5 chat models, bfloat16 45.4%
- 282 princeton-nlp Llama-3-Instruct-8B-SimPO-v0.2 chat models, bfloat16 45.3%
- 283 Ashmal MBZUAI-ORYX-new , float16 45.2%
- 284 chujiezheng Mistral7B-PairRM-SPPO-ExPO chat models, bfloat16 45.1%
- 285
Qwen1.5-14B-Chat pretrained, bfloat16 45.1%
- 286 Artples L-MChat-7b base merges and moerges, bfloat16 44.9%
- 287 upstage SOLAR-10.7B-v1.0 pretrained, float16 44.9%
- 288 UCLA-AGI Mistral7B-PairRM-SPPO chat models, bfloat16 44.9%
- 289 UCLA-AGI Mistral7B-PairRM-SPPO-Iter1 chat models, bfloat16 44.8%
- 290 princeton-nlp Mistral-7B-Base-SFT-SLiC-HF chat models, bfloat16 44.8%
- 291 RDson WomboCombo-R1-Coder-14B-Preview base merges and moerges, bfloat16 44.7%
- 292 princeton-nlp Llama-3-Base-8B-SFT-SLiC-HF chat models, bfloat16 44.6%
- 293 Syed-Hasan-8503 Phi-3-mini-4K-instruct-cpo-simpo chat models, bfloat16 44.5%
- 294 OpenBuddy openbuddy-llama3.1-8b-v22.3-131k chat models, bfloat16 44.5%
- 295 UCLA-AGI Mistral7B-PairRM-SPPO-Iter2 chat models, bfloat16 44.4%
- 296 cognitivecomputations dolphin-2.6-mixtral-8x7b fine-tuned on domain-specific datasets, bfloat16 44.4%
- 297 riotu-lab ArabianGPT-03B , ? 44.2%
- 298 TIGER-Lab MAmmoTH2-8B-Plus fine-tuned on domain-specific datasets, bfloat16 44.2%
- 299 migtissera Tess-M-v1.3 fine-tuned on domain-specific datasets, float16 44.2%
- 300 01-ai/Yi-9B-200K pretrained, bfloat16 44.2%
- 301 jondurbin airoboros-dpo-70b-3.3 chat models, bfloat16 44.2%
- 302 openchat openchat-3.5-0106-gemma chat models, bfloat16 44.2%
- 303 inceptionai jais-adapted-13b-chat chat models, float16 44.1%
- 304 cognitivecomputations dolphin-2.9.3-mistral-nemo-12b fine-tuned on domain-specific datasets, bfloat16 44%
- 305 FreedomIntelligence AceGPT-13B-chat chat models, float16 44%
- 306
Qwen2.5-14B pretrained, bfloat16 44%
- 307 princeton-nlp Mistral-7B-Instruct-DPO chat models, bfloat16 43.8%
- 308 FreedomIntelligence AceGPT-7B pretrained, float16 43.8%
- 309 sajaw llama-2-7b-RandomGPT-5K-ar , bfloat16 43.7%
- 310 lemon-mint gemma-ko-7b-instruct-v0.62 fine-tuned on domain-specific datasets, bfloat16 43.7%
- 311 meta-llama/Llama-2-13b-hf pretrained, float16 43.6%
- 312 jondurbin airoboros-70b-3.3 chat models, bfloat16 43.6%
- 313 princeton-nlp Mistral-7B-Base-SFT-CPO chat models, bfloat16 43.6%
- 314 UCLA-AGI Mistral7B-PairRM-SPPO-Iter3 chat models, bfloat16 43.5%
- 315 cstr llama3-8b-spaetzle-v37 base merges and moerges, bfloat16 43.5%
- 316 elmrc JuhainaG9B chat models, bfloat16 43.5%
- 317 EpistemeAI Fireball-Alpaca-Llama-3.1-8B-Philos-DPO-200 chat models, float16 43.5%
- 318 arcee-ai Llama-3.1-SuperNova-Lite fine-tuned on domain-specific datasets, bfloat16 43.5%
- 319 princeton-nlp gemma-2-9b-it-SimPO chat models, bfloat16 43.5%
- 320 MaziyarPanahi Llama-3-8B-Instruct-v0.10 chat models, bfloat16 43.4%
- 321 leafspark Llama-3.1-8B-MultiReflection-Instruct chat models, float16 43.4%
- 322 princeton-nlp Llama-3-Base-8B-SFT-ORPO chat models, bfloat16 43.4%
- 323 princeton-nlp Mistral-7B-Instruct-RDPO chat models, bfloat16 43.3%
- 324 migtissera Tess-v2.5.2-Qwen2-72B fine-tuned on domain-specific datasets, bfloat16 43.3%
- 325 meta-llama/Llama-2-70b-hf pretrained, float16 43.3%
- 326 abhishek autotrain-llama3-70b-orpo-v2 chat models, float16 43.2%
- 327 DeepMount00 Llama-3.1-8b-Ita fine-tuned on domain-specific datasets, bfloat16 43.2%
- 328
Mistral-7B-Instruct-v0.2 chat models, bfloat16 43.2%
- 329 EpistemeAI Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1-KTO-beta chat models, float16 43.2%
- 330 EpistemeAI Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-beta chat models, float16 43.1%
- 331 gbueno86 Meta-LLama-3-Cat-Smaug-LLama-70b base merges and moerges, bfloat16 43.1%
- 332 mlabonne NeuralDaredevil-8B-abliterated chat models, float16 43.1%
- 333 arcee-ai Virtuoso-Small chat models, bfloat16 43.1%
- 334 cognitivecomputations dolphin-2.9.1-yi-1.5-9b fine-tuned on domain-specific datasets, bfloat16 43.1%
- 335 airev-ai Jais-Inception-7b-V0.1 chat models, bfloat16 43%
- 336 failspy Meta-Llama-3-70B-Instruct-abliterated-v3.5 fine-tuned on domain-specific datasets, bfloat16 43%
- 337 Isaak-Carter Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 fine-tuned on domain-specific datasets, bfloat16 43%
- 338 abacusai Smaug-72B-v0.1 chat models, bfloat16 43%
- 339 cognitivecomputations dolphin-2.9.1-llama-3-70b fine-tuned on domain-specific datasets, bfloat16 43%
- 340 inceptionai jais-family-30b-16k-chat chat models, float16 43%
- 341 abacusai Smaug-Mixtral-v0.1 , ? 43%
- 342 BAAI Infinity-Instruct-3M-0625-Yi-1.5-9B chat models, bfloat16 42.9%
- 343 recoilme Gemma-2-Ataraxy-Gemmasutra-9B-slerp base merges and moerges, bfloat16 42.9%
- 344 EpistemeAI2 Fireball-Alpaca-Llama-3.1-8B-Instruct-KTO-beta chat models, float16 42.9%
- 345 freewheelin free-llama3-dpo-v0.2 chat models, bfloat16 42.8%
- 346 arcee-ai Llama-Spark , ? 42.8%
- 347 meta-llama/Meta-Llama-3.1-8B-Instruct chat models, bfloat16 42.8%
- 348 ClusterlabAi GemmAr-7B-v1 chat models, float16 42.8%
- 349 AXCXEPT EZO-Qwen2.5-72B-Instruct fine-tuned on domain-specific datasets, bfloat16 42.6%
- 350 paloalma Le_Triomphant-ECE-TW3 base merges and moerges, bfloat16 42.6%
- 351 cognitivecomputations dolphin-2.9.3-llama-3-8b fine-tuned on domain-specific datasets, bfloat16 42.6%
- 352
Aya Expanse 8B chat models, float16 42.6%
- 353 VAGOsolutions Llama-3.1-SauerkrautLM-8b-Instruct fine-tuned on domain-specific datasets, bfloat16 42.6%
- 354 Steelskull L3-MS-Astoria-70b base merges and moerges, bfloat16 42.5%
- 355 tanliboy lambda-qwen2.5-32b-dpo-test chat models, bfloat16 42.5%
- 356 openchat openchat-3.5-0106 chat models, bfloat16 42.4%
- 357 vicgalle Configurable-Llama-3.1-8B-Instruct chat models, float16 42.4%
- 358 pankajmathur orca_mini_v7_72b chat models, bfloat16 42.4%
- 359 MaziyarPanahi Llama-3-8B-Instruct-v0.9 chat models, bfloat16 42.4%
- 360 Qwen/Qwen2.5-Math-7B pretrained, bfloat16 42.4%
- 361 princeton-nlp Mistral-7B-Instruct-KTO chat models, bfloat16 42.4%
- 362 inceptionai jais-adapted-70b-chat chat models, float16 42.4%
- 363 bunnycore HyperLlama-3.1-8B base merges and moerges, bfloat16 42.3%
- 364 brucethemoose Yi-34B-200K-DARE-merge-v7 base merges and moerges, bfloat16 42.3%
- 365 cognitivecomputations dolphin-2.9.2-Phi-3-Medium chat models, bfloat16 42.2%
- 366 anthracite-org magnum-v3-9b-customgemma2 chat models, bfloat16 42.2%
- 367 mssqpi G3 chat models, bfloat16 42.2%
- 368 princeton-nlp Llama-3-Instruct-8B-IPO-v0.2 chat models, bfloat16 42.2%
- 369 silma-ai SILMA-9B-Instruct-v0.1 chat models, bfloat16 42.2%
- 370 silma-ai SILMA-9B-Instruct-v0.1.0 chat models, bfloat16 42.2%
- 371 silma-ai SILMA-9B-Instruct-v0.1.1 pretrained, bfloat16 42.2%
- 372 RLHFlow LLaMA3-iterative-DPO-final chat models, bfloat16 42.1%
- 373 Orenguteng Llama-3.1-8B-Lexi-Uncensored-V2 fine-tuned on domain-specific datasets, bfloat16 42.1%
- 374 lightblue suzume-llama-3-8B-multilingual-orpo-borda-full chat models, bfloat16 42%
- 375 mlabonne Daredevil-8B-abliterated fine-tuned on domain-specific datasets, bfloat16 42%
- 376 princeton-nlp Llama-3-Instruct-8B-KTO-v0.2 chat models, bfloat16 42%
- 377
Falcon3-3B-Instruct chat models, bfloat16 41.9%
- 378 BAAI Infinity-Instruct-3M-0613-Mistral-7B fine-tuned on domain-specific datasets, bfloat16 41.9%
- 379 deepseek-ai/DeepSeek-R1-Distill-Llama-8B fine-tuned on domain-specific datasets, bfloat16 41.9%
- 380 cognitivecomputations openchat-3.5-0106-laser fine-tuned on domain-specific datasets, bfloat16 41.9%
- 381 dnhkng RYS-Llama-3.1-8B-Instruct fine-tuned on domain-specific datasets, bfloat16 41.9%
- 382 Magpie-Align Llama-3-8B-Magpie-Align-SFT-v0.3 fine-tuned on domain-specific datasets, bfloat16 41.9%
- 383 Orenguteng Llama-3.1-8B-Lexi-Uncensored fine-tuned on domain-specific datasets, bfloat16 41.9%
- 384 wenbopan Faro-Yi-9B fine-tuned on domain-specific datasets, bfloat16 41.8%
- 385 rombodawg Everyone-Coder-4x7b-Base , bfloat16 41.8%
- 386 axolotl-ai-co romulus-mistral-nemo-12b-simpo chat models, bfloat16 41.8%
- 387 cognitivecomputations dolphin-2.9.2-Phi-3-Medium-abliterated fine-tuned on domain-specific datasets, bfloat16 41.7%
- 388 tiiuae/falcon-11B pretrained, bfloat16 41.7%
- 389 grimjim Llama-3.1-8B-Instruct-abliterated_via_adapter base merges and moerges, bfloat16 41.7%
- 390 SeaLLMs SeaLLM-7B-v2.5 fine-tuned on domain-specific datasets, bfloat16 41.7%
- 391 vicgalle Configurable-Hermes-2-Pro-Llama-3-8B chat models, float16 41.7%
- 392 CohereForAI/aya-23-35B fine-tuned on domain-specific datasets, float16 41.6%
- 393 FreedomIntelligence AceGPT-13B pretrained, float16 41.6%
- 394 uukuguy zephyr-7b-alpha-dare-0.85 fine-tuned on domain-specific datasets, float16 41.6%
- 395 princeton-nlp gemma-2-9b-it-DPO , bfloat16 41.6%
- 396 tiiuae/Falcon3-7B-Base pretrained, bfloat16 41.6%
- 397 cognitivecomputations dolphin-2.9.3-mistral-7B-32k fine-tuned on domain-specific datasets, bfloat16 41.5%
- 398
Qwen2.5-Coder (7B) pretrained, bfloat16 41.5%
- 399
Falcon3-1B-Instruct chat models, bfloat16 41.5%
- 400 uygarkurt llama-3-merged-linear base merges and moerges, float16 41.5%
- 401 Magpie-Align MagpieLM-8B-Chat-v0.1 chat models, bfloat16 41.4%
- 402
Gemma 2 9B , ? 41.4%
- 403 recoilme recoilme-gemma-2-9B-v0.2 fine-tuned on domain-specific datasets, bfloat16 41.4%
- 404 VAGOsolutions Llama-3-SauerkrautLM-8b-Instruct chat models, bfloat16 41.4%
- 405 princeton-nlp Llama-3-Instruct-8B-RDPO chat models, bfloat16 41.4%
- 406 DeepMount00 Llama-3-8b-Ita fine-tuned on domain-specific datasets, bfloat16 41.3%
- 407 FiditeNemini Unhinged-Qwen2-72B base merges and moerges, bfloat16 41.3%
- 408 MaziyarPanahi Llama-3-8B-Instruct-v0.8 chat models, bfloat16 41.3%
- 409 princeton-nlp Llama-3-Instruct-8B-DPO chat models, bfloat16 41.3%
- 410 princeton-nlp Llama-3-Instruct-8B-CPO-v0.2 chat models, bfloat16 41.3%
- 411 vicgalle Configurable-Janus-7B chat models, float16 41.2%
- 412 jondurbin bagel-8b-v1.0 fine-tuned on domain-specific datasets, bfloat16 41.2%
- 413 Isaak-Carter Josiefied-Qwen2.5-7B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 41.1%
- 414 TheDrummer Gemmasutra-9B-v1 base merges and moerges, bfloat16 41.1%
- 415 princeton-nlp Mistral-7B-Instruct-IPO chat models, bfloat16 41%
- 416 amazon MegaBeam-Mistral-7B-300k fine-tuned on domain-specific datasets, bfloat16 41%
- 417 Dampfinchen Llama-3.1-8B-Ultra-Instruct base merges and moerges, bfloat16 41%
- 418 VAGOsolutions SauerkrautLM-Gemma-7b chat models, bfloat16 41%
- 419 BAAI Infinity-Instruct-3M-0625-Llama3-8B chat models, bfloat16 41%
- 420 migtissera Tess-3-Mistral-Nemo-12B fine-tuned on domain-specific datasets, bfloat16 40.9%
- 421 NotAiLOL Yi-1.5-dolphin-9B fine-tuned on domain-specific datasets, bfloat16 40.9%
- 422 princeton-nlp Llama-3-Base-8B-SFT-RRHF chat models, bfloat16 40.9%
- 423 princeton-nlp Llama-3-Base-8B-SFT fine-tuned on domain-specific datasets, bfloat16 40.9%
- 424 inceptionai jais-adapted-70b chat models, float16 40.9%
- 425 uukuguy speechless-zephyr-code-functionary-7b fine-tuned on domain-specific datasets, bfloat16 40.8%
- 426 airev-ai Jais-Inception-70b , bfloat16 40.8%
- 427 anthracite-org magnum-v3-9b-chatml chat models, bfloat16 40.8%
- 428 618AI dictalm2-it-qa-fine-tune , bfloat16 40.8%
- 429 TIGER-Lab MAmmoTH2-7B-Plus fine-tuned on domain-specific datasets, bfloat16 40.7%
- 430 migtissera Tess-3-Llama-3.1-70B fine-tuned on domain-specific datasets, bfloat16 40.7%
- 431 OpenBuddy openbuddy-qwen2.5llamaify-14b-v23.1-200k chat models, bfloat16 40.7%
- 432 Eurdem Defne-llama3.1-8B base merges and moerges, bfloat16 40.7%
- 433 princeton-nlp Llama-3-Instruct-8B-KTO chat models, bfloat16 40.7%
- 434 Replete-AI Replete-LLM-V2.5-Qwen-32b fine-tuned on domain-specific datasets, bfloat16 40.7%
- 435 ValiantLabs Llama3.1-8B-ShiningValiant2 , ? 40.7%
- 436 NousResearch Hermes-2-Theta-Llama-3-8B chat models, bfloat16 40.7%
- 437 Qwen/Qwen2.5-32B-Instruct chat models, bfloat16 40.7%
- 438 v000000 L3.1-Niitorm-8B-DPO-t0.0001 chat models, float16 40.6%
- 439 meta-llama/Llama-3.2-3B-Instruct chat models, bfloat16 40.6%
- 440 princeton-nlp Llama-3-Base-8B-SFT-CPO chat models, bfloat16 40.6%
- 441 core42 jais-13b-chat , ? 40.6%
- 442 princeton-nlp Llama-3-Instruct-8B-SimPO chat models, bfloat16 40.6%
- 443
Gemma 2B pretrained, bfloat16 40.6%
- 444 core42 jais-30b-chat-v1 , ? 40.6%
- 445 FreedomIntelligence AceGPT-v2-8B-Chat chat models, float16 40.6%
- 446 inceptionai jais-family-6p7b-chat , ? 40.6%
- 447 princeton-nlp Llama-3-Instruct-8B-ORPO-v0.2 chat models, bfloat16 40.6%
- 448 silma-ai SILMA-Kashif-2B-Instruct-v1.0 chat models, bfloat16 40.6%
- 449 Sakalti ultiima-32B base merges and moerges, float16 40.5%
- 450 Qwen2.5-Coder-14B pretrained, bfloat16 40.5%
- 451 uukuguy speechless-code-mistral-7b-v1.0 fine-tuned on domain-specific datasets, float16 40.5%
- 452 c4ai-command-r-08-2024 chat models, float16 40.5%
- 453 inceptionai jais-adapted-7b-chat , ? 40.5%
- 454 TIGER-Lab MAmmoTH2-8x7B-Plus fine-tuned on domain-specific datasets, bfloat16 40.5%
- 455 cognitivecomputations dolphin-2.9.2-qwen2-72b chat models, bfloat16 40.4%
- 456 BAAI OPI-Llama-3.1-8B-Instruct fine-tuned on domain-specific datasets, bfloat16 40.4%
- 457 Ba2han QwQenSeek-coder base merges and moerges, bfloat16 40.4%
- 458 cognitivecomputations dolphin-2.9.1-llama-3-8b fine-tuned on domain-specific datasets, bfloat16 40.4%
- 459 cognitivecomputations Llama-3-8B-Instruct-abliterated-v2 fine-tuned on domain-specific datasets, bfloat16 40.4%
- 460 Ali-C137 Ge1H10M-0000 pretrained, bfloat16 40.4%
- 461 inceptionai jais-family-2p7b-chat , ? 40.4%
- 462 mlabonne ChimeraLlama-3-8B-v2 base merges and moerges, float16 40.4%
- 463 failspy Smaug-Llama-3-70B-Instruct-abliterated-v3 fine-tuned on domain-specific datasets, bfloat16 40.4%
- 464 maldv Qwenstein2.5-32B-Instruct base merges and moerges, bfloat16 40.4%
- 465 gbueno86 Meta-LLama-3-Cat-A-LLama-70b base merges and moerges, bfloat16 40.4%
- 466 princeton-nlp Llama-3-Instruct-8B-RRHF-v0.2 chat models, bfloat16 40.4%
- 467 princeton-nlp Llama-3-Instruct-8B-SLiC-HF-v0.2 chat models, bfloat16 40.4%
- 468 princeton-nlp Mistral-7B-Instruct-CPO chat models, bfloat16 40.3%
- 469 huihui-ai Qwen2.5-7B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 40.3%
- 470 inceptionai jais-family-30b-8k-chat , ? 40.3%
- 471 FreedomIntelligence AceGPT-v2-70B pretrained, float16 40.3%
- 472 sambanovasystems SambaLingo-Arabic-Chat chat models, bfloat16 40.3%
- 473 01-ai/Yi-1.5-9B-32K pretrained, bfloat16 40.3%
- 474 google/gemma-7b-it fine-tuned on domain-specific datasets, bfloat16 40.3%
- 475 grimjim Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge base merges and moerges, bfloat16 40.3%
- 476 kaist-ai mistral-orpo-capybara-7k chat models, bfloat16 40.3%
- 477 nbeerbower DeepSeek-R1-Qwen-lorablated-32B base merges and moerges, bfloat16 40.3%
- 478
Gemma 7B pretrained, bfloat16 40.2%
- 479 grimjim Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge base merges and moerges, bfloat16 40.2%
- 480
Gemma 1.1 7B IT chat models, bfloat16 40.2%
- 481 BAAI Infinity-Instruct-7M-Gen-Llama3_1-70B fine-tuned on domain-specific datasets, bfloat16 40.2%
- 482
Llama 3.1-70B pretrained, bfloat16 40.2%
- 483 GritLM GritLM-8x7B-KTO chat models, bfloat16 40.2%
- 484 ibivibiv llama-3-nectar-dpo-8B , ? 40.2%
- 485 Magpie-Align MagpieLM-8B-SFT-v0.1 fine-tuned on domain-specific datasets, bfloat16 40.2%
- 486 qnguyen3 Master-Yi-9B chat models, bfloat16 40.2%
- 487 Daemontatox MawaredT1 , bfloat16 40.2%
- 488 EpistemeAI2 Fireball-Llama-3.1-8B-Philos-Relection fine-tuned on domain-specific datasets, float16 40.1%
- 489 tiiuae/Falcon3-10B-Base pretrained, bfloat16 40.1%
- 490 nbeerbower mistral-nemo-wissenschaft-12B chat models, bfloat16 40.1%
- 491
Gemma 1.1 2B IT chat models, bfloat16 40.1%
- 492 Kukedlc NeuralLLaMa-3-8b-ORPO-v0.3 chat models, float16 40.1%
- 493
Falcon-40B pretrained, bfloat16 40.1%
- 494 core42 jais-30b-chat-v3 , ? 40.1%
- 495 failspy Codestral-22B-v0.1-abliterated-v3 fine-tuned on domain-specific datasets, bfloat16 40.1%
- 496 NLPark AnFeng_v3.1-Avocet chat models, float16 40.1%
- 497 Ali-C137 F1H10M-0000 pretrained, bfloat16 40.1%
- 498
Falcon-7B pretrained, bfloat16 40.1%
- 499 Kukedlc NeuralLLaMa-3-8b-DT-v0.1 base merges and moerges, float16 40.1%
- 500 migtissera Llama-3-70B-Synthia-v3.5 fine-tuned on domain-specific datasets, float16 40.1%
- 501 princeton-nlp Mistral-7B-Base-SFT-KTO chat models, bfloat16 40.1%
- 502 OpenBuddy openbuddy-qwen2.5llamaify-7b-v23.1-200k chat models, bfloat16 40.1%
- 503 migtissera Tess-v2.5-Qwen2-72B fine-tuned on domain-specific datasets, float16 40.1%
- 504 01-ai/Yi-1.5-9B pretrained, bfloat16 40.1%
- 505 princeton-nlp Llama-3-Instruct-8B-CPO chat models, bfloat16 40.1%
- 506 terrycraddock Reflection-Llama-3.1-8B chat models, float16 40.1%
- 507 yellowtown 7B-v0.2 fine-tuned on domain-specific datasets, bfloat16 40.1%
- 508 maywell Synatra-7B-v0.3-RP fine-tuned on domain-specific datasets, float16 40%
- 509 SakanaAI DiscoPOP-zephyr-7b-gemma chat models, bfloat16 40%
- 510 kaist-ai janus-rm-7b fine-tuned on domain-specific datasets, bfloat16 40%
- 511 GritLM GritLM-8x7B fine-tuned on domain-specific datasets, bfloat16 40%
- 512 riotu-lab ArabianGPT-08B-V2 , ? 40%
- 513 MarinaraSpaghetti NemoReRemix-12B base merges and moerges, bfloat16 40%
- 514 huihui-ai DeepSeek-R1-Distill-Qwen-32B-abliterated fine-tuned on domain-specific datasets, bfloat16 40%
- 515 Ali-C137 L2H10M-0000 pretrained, bfloat16 40%
- 516 kaist-ai janus-dpo-7b chat models, bfloat16 40%
- 517 Magpie-Align Llama-3.1-8B-Magpie-Align-SFT-v0.1 fine-tuned on domain-specific datasets, bfloat16 40%
- 518 meta-llama/Llama-2-7b-hf pretrained, float16 40%
- 519 princeton-nlp Mistral-7B-Base-SFT-RRHF chat models, bfloat16 40%
- 520 Danielbrdz Barcenas-Llama3-8b-ORPO chat models, float16 40%
- 521 kaist-ai janus-7b fine-tuned on domain-specific datasets, bfloat16 40%
- 522 NTQAI Nxcode-CQ-7B-orpo chat models, bfloat16 40%
- 523 princeton-nlp Llama-3-8B-ProLong-64k-Instruct , ? 40%
- 524 SenseLLM ReflectionCoder-CL-34B chat models, bfloat16 40%
- 525 google/gemma-2b-it fine-tuned on domain-specific datasets, bfloat16 40%
- 526 MaziyarPanahi Mistral-7B-Instruct-v0.3 fine-tuned on domain-specific datasets, bfloat16 40%
- 527 migtissera Tess-2.0-Llama-3-70B fine-tuned on domain-specific datasets, float16 40%
- 528 mistralai/Mistral-7B-Instruct-v0.3 fine-tuned on domain-specific datasets, bfloat16 40%
- 529 utter-project EuroLLM-9B-Instruct chat models, bfloat16 40%
- 530 abacusai bigstral-12b-32k base merges and moerges, float16 40%
- 531 FreedomIntelligence AceGPT-v1.5-13B , ? 39.9%
- 532 princeton-nlp Mistral-7B-Instruct-ORPO chat models, bfloat16 39.9%
- 533 princeton-nlp Mistral-7B-Instruct-SLiC-HF chat models, bfloat16 39.9%
- 534 inceptionai jais-adapted-13b , ? 39.9%
- 535 princeton-nlp Llama-3-8B-ProLong-512k-Instruct , ? 39.9%
- 536 meta-llama/Meta-Llama-3-8B-Instruct fine-tuned on domain-specific datasets, float16 39.9%
- 537 Triangle104 DeepSky-T100 base merges and moerges, float16 39.9%
- 538
Llama 3.2 1B pretrained, bfloat16 39.9%
- 539 ghost-x ghost-8b-beta-1608 chat models, bfloat16 39.9%
- 540 mlabonne ChimeraLlama-3-8B-v3 base merges and moerges, float16 39.9%
- 541 UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter3 chat models, bfloat16 39.9%
- 542 2A2I-R L1000MT pretrained, bfloat16 39.9%
- 543 2A2I-R L100MT pretrained, bfloat16 39.9%
- 544 2A2I-R L200MT pretrained, bfloat16 39.9%
- 545 2A2I-R L500MT pretrained, bfloat16 39.9%
- 546 SicariusSicariiStuff Qwen2.5-14B_Uncencored fine-tuned on domain-specific datasets, float16 39.9%
- 547 UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter1 chat models, bfloat16 39.9%
- 548 dicta-il dictalm2.0-instruct chat models, bfloat16 39.9%
- 549 UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter2 chat models, bfloat16 39.9%
- 550 HeshamHaroon llama-3-instruct-slerp-arabic , bfloat16 39.8%
- 551 anthracite-org magnum-v2.5-12b-kto chat models, float16 39.8%
- 552 bigscience bloom-7b1 pretrained, float16 39.8%
- 553 lightblue suzume-llama-3-8B-multilingual fine-tuned on domain-specific datasets, bfloat16 39.8%
- 554 lightblue suzume-llama-3-8B-multilingual-orpo-borda-top25 chat models, bfloat16 39.8%
- 555 OpenBuddy openbuddy-llama3-70b-v21.2-32k chat models, bfloat16 39.8%
- 556 paloalma ECE-TW3-JRGL-V3 base merges and moerges, bfloat16 39.8%
- 557 princeton-nlp Llama-3-Instruct-8B-IPO chat models, bfloat16 39.8%
- 558 vicgalle Configurable-Llama-3-8B-v0.3 chat models, float16 39.8%
- 559 failspy Meta-Llama-3-8B-Instruct-abliterated-v3 fine-tuned on domain-specific datasets, bfloat16 39.8%
- 560 FreedomIntelligence AceGPT-v2-32B-Chat chat models, float16 39.8%
- 561 google/recurrentgemma-2b-it chat models, bfloat16 39.8%
- 562 CohereForAI/c4ai-command-r-plus-08-2024 chat models, float16 39.8%
- 563 Sakalti Saka-24B base merges and moerges, float16 39.8%
- 564
Llama 3.1-8B pretrained, bfloat16 39.8%
- 565
DeepSeek-R1-Distill-Qwen-7B fine-tuned on domain-specific datasets, bfloat16 39.8%
- 566 FreedomIntelligence AceGPT-v1.5-13B-Chat , ? 39.8%
- 567 gaverfraxz Meta-Llama-3.1-8B-Instruct-HalfAbliterated-TIES base merges and moerges, float16 39.8%
- 568 princeton-nlp Llama-3-Instruct-8B-RRHF chat models, bfloat16 39.8%
- 569 princeton-nlp Llama-3-Instruct-8B-SLiC-HF chat models, bfloat16 39.8%
- 570 v000000 SwallowMaid-8B-L3-SPPO-abliterated , ? 39.8%
- 571 cognitivecomputations dolphin-2.7-mixtral-8x7b fine-tuned on domain-specific datasets, bfloat16 39.8%
- 572 speakleash Bielik-11B-v2.3-Instruct base merges and moerges, float16 39.8%
- 573 aws-prototyping MegaBeam-Mistral-7B-512k fine-tuned on domain-specific datasets, bfloat16 39.8%
- 574 ibivibiv llama3-8b-instruct-summary-combined , ? 39.8%
- 575 Delta-Vector Odin-9B fine-tuned on domain-specific datasets, bfloat16 39.7%
- 576 dfurman Llama-3-70B-Orpo-v0.1 chat models, float16 39.7%
- 577 recoilme recoilme-gemma-2-9B-v0.3 fine-tuned on domain-specific datasets, bfloat16 39.7%
- 578 BAAI Infinity-Instruct-7M-Gen-Llama3_1-8B fine-tuned on domain-specific datasets, bfloat16 39.7%
- 579 migtissera Tess-2.0-Llama-3-70B-v0.2 fine-tuned on domain-specific datasets, float16 39.7%
- 580 Nohobby Q2.5-Qwetiapin-32B base merges and moerges, bfloat16 39.7%
- 581
Llama 3-70B pretrained, bfloat16 39.7%
- 582 abacusai bigyi-15b base merges and moerges, float16 39.7%
- 583 ai21labs AI21-Jamba-1.5-Mini pretrained, bfloat16 39.7%
- 584 CohereForAI/c4ai-command-r-plus fine-tuned on domain-specific datasets, float16 39.7%
- 585 kaist-ai janus-orpo-7b chat models, bfloat16 39.7%
- 586 tokyotech-llm Llama-3-Swallow-8B-Instruct-v0.1 fine-tuned on domain-specific datasets, bfloat16 39.7%
- 587 GritLM GritLM-7B fine-tuned on domain-specific datasets, bfloat16 39.7%
- 588 rombodawg rombos_Replete-Coder-Instruct-8b-Merged base merges and moerges, bfloat16 39.7%
- 589
Qwen2.5-32B pretrained, bfloat16 39.7%
- 590 core42 jais-30b-v1 , ? 39.7%
- 591 core42 jais-30b-v3 , ? 39.7%
- 592 inceptionai jais-family-30b-8k , ? 39.7%
- 593 princeton-nlp Llama-3-Instruct-8B-ORPO chat models, bfloat16 39.7%
- 594 sambanovasystems SambaLingo-Arabic-Base-70B , ? 39.7%
- 595 utter-project EuroLLM-9B pretrained, bfloat16 39.7%
- 596
Qwen1.5-7B-Chat pretrained, bfloat16 39.7%
- 597 SeaLLMs SeaLLMs-v3-7B-Chat chat models, bfloat16 39.7%
- 598 anthracite-org magnum-v4-9b chat models, bfloat16 39.7%
- 599 Qwen/Qwen2.5-7B-Instruct chat models, bfloat16 39.7%
- 600 abacusai Llama-3-Smaug-8B fine-tuned on domain-specific datasets, bfloat16 39.6%
- 601 inceptionai jais-family-1p3b-chat , ? 39.6%
- 602 natong19 Mistral-Nemo-Instruct-2407-abliterated fine-tuned on domain-specific datasets, bfloat16 39.6%
- 603 OpenBuddy openbuddy-yi1.5-34b-v21.6-32k-fp16 chat models, float16 39.6%
- 604 Replete-AI Replete-LLM-V2.5-Qwen-7b fine-tuned on domain-specific datasets, bfloat16 39.6%
- 605 Ali-C137 M03H10M-0000 pretrained, bfloat16 39.6%
- 606 MaziyarPanahi Mistral-7B-v0.3 pretrained, bfloat16 39.6%
- 607 nyunai nyun-c2-llama3-56B fine-tuned on domain-specific datasets, float16 39.6%
- 608
Mistral 7B v0.3 pretrained, bfloat16 39.6%
- 609
DeepSeek-R1-Distill-Qwen-14B fine-tuned on domain-specific datasets, bfloat16 39.6%
- 610 inceptionai jais-adapted-7b , ? 39.6%
- 611 Kukedlc NeuralLLaMa-3-8b-ORPO-v0.4 chat models, float16 39.6%
- 612 sambanovasystems SambaLingo-Arabic-Base , ? 39.6%
- 613 turboderp Cat-Llama-3-70B-instruct chat models, float16 39.6%
- 614 dfurman Llama-3-8B-Orpo-v0.1 chat models, float16 39.6%
- 615 inceptionai jais-family-30b-16k , ? 39.6%
- 616 MaziyarPanahi calme-2.3-qwen2-72b chat models, bfloat16 39.6%
- 617 MaziyarPanahi calme-2.3-qwen2-7b fine-tuned on domain-specific datasets, bfloat16 39.6%
- 618 Qwen/Qwen2.5-3B-Instruct chat models, bfloat16 39.6%
- 619 speakleash Bielik-11B-v2 pretrained, bfloat16 39.6%
- 620 vicgalle Configurable-Hermes-3-Llama-3.1-8B chat models, float16 39.6%
- 621 maywell Qwen2-7B-Multilingual-RP fine-tuned on domain-specific datasets, bfloat16 39.6%
- 622 MaziyarPanahi calme-2.2-qwen2-7b fine-tuned on domain-specific datasets, bfloat16 39.6%
- 623 MaziyarPanahi calme-2.4-qwen2-7b fine-tuned on domain-specific datasets, bfloat16 39.6%
- 624 prithivMLmods Qwen2.5-32B-DeepSeek-R1-Instruct base merges and moerges, bfloat16 39.6%
- 625 RDson CoderO1-DeepSeekR1-Coder-32B-Preview base merges and moerges, bfloat16 39.6%
- 626 riotu-lab ArabianGPT-1.5B , ? 39.6%
- 627 GritLM GritLM-7B-KTO chat models, bfloat16 39.6%
- 628 Sakalti Saka-7.6B base merges and moerges, float16 39.6%
- 629 sambanovasystems SambaLingo-Arabic-Chat-70B , ? 39.6%
- 630 SicariusSicariiStuff Qwen2.5-14B_Uncensored_Instruct chat models, float16 39.6%
- 631 arcee-ai Arcee-Spark chat models, bfloat16 39.6%
- 632 mlabonne FineLlama-3.1-8B fine-tuned on domain-specific datasets, bfloat16 39.6%
- 633 mlabonne Meta-Llama-3.1-8B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 39.6%
- 634 NaniDAO deepseek-r1-qwen-2.5-32B-ablated fine-tuned on domain-specific datasets, bfloat16 39.6%
- 635 NousResearch Hermes-3-Llama-3.1-8B chat models, bfloat16 39.6%
- 636
Qwen2.5-1.5B pretrained, bfloat16 39.6%
- 637 dicta-il dictalm2.0 pretrained, bfloat16 39.6%
- 638 MohamedRashad Arabic-Orpo-Llama-3-8B-Instruct fine-tuned on domain-specific datasets, float16 39.6%
- 639
Qwen1.5-72B pretrained, bfloat16 39.6%
- 640 Ali-C137 PG7BB pretrained, bfloat16 39.5%
- 641 Ali-C137 Q2AW1M-0000 pretrained, bfloat16 39.5%
- 642 Ali-C137 Q2AW1M-0010 pretrained, bfloat16 39.5%
- 643 Ali-C137 Q2AW1M-0100 pretrained, bfloat16 39.5%
- 644 Ali-C137 Q2AW1M-1000 pretrained, bfloat16 39.5%
- 645 Ali-C137 Q2AW1M-1010 pretrained, bfloat16 39.5%
- 646 Ali-C137 Q2AW1M-1100 pretrained, bfloat16 39.5%
- 647 Ali-C137 Q2H10M-0000 pretrained, bfloat16 39.5%
- 648 informatiker Qwen2-7B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 39.5%
- 649 MaziyarPanahi calme-2.5-qwen2-7b fine-tuned on domain-specific datasets, bfloat16 39.5%
- 650 natong19 Qwen2-7B-Instruct-abliterated fine-tuned on domain-specific datasets, bfloat16 39.5%
- 651 prithivMLmods Qwen2.5-14B-DeepSeek-R1-1M base merges and moerges, bfloat16 39.5%
- 652
Qwen2-7B-Instruct chat models, bfloat16 39.5%
- 653
Qwen2.5-3B pretrained, bfloat16 39.5%
- 654
Qwen2.5-7B pretrained, bfloat16 39.5%
- 655 inceptionai jais-family-590m-chat , ? 39.5%
- 656 VAGOsolutions SauerkrautLM-Nemo-12b-Instruct fine-tuned on domain-specific datasets, bfloat16 39.5%
- 657 cognitivecomputations dolphin-2.9.4-llama3.1-8b fine-tuned on domain-specific datasets, bfloat16 39.5%
- 658 FreedomIntelligence AceGPT-v2-70B-Chat chat models, float16 39.5%
- 659 nicoboss DeepSeek-R1-Distill-Qwen-32B-Uncensored fine-tuned on domain-specific datasets, bfloat16 39.5%
- 660 tiiuae/Falcon3-3B-Base pretrained, bfloat16 39.5%
- 661
Qwen2-7B pretrained, bfloat16 39.5%
- 662 AXCXEPT EZO-Qwen2.5-32B-Instruct fine-tuned on domain-specific datasets, bfloat16 39.5%
- 663 inceptionai jais-family-13b , ? 39.5%
- 664 NousResearch Nous-Hermes-2-Mixtral-8x7B-DPO chat models, bfloat16 39.5%
- 665 Qwen/Qwen2-MoE-57B-A14B , bfloat16 39.5%
- 666
Qwen1.5-14B pretrained, bfloat16 39.5%
- 667 abacusai Liberated-Qwen1.5-14B fine-tuned on domain-specific datasets, float16 39.5%
- 668 AIDC-AI Marco-LLM-AR pretrained, bfloat16 39.5%
- 669 Ali-C137 Q2AW1M-0001 pretrained, bfloat16 39.5%
- 670 Ali-C137 Q2AW1M-0111 pretrained, bfloat16 39.5%
- 671 Ali-C137 Q2AW1M-1001 pretrained, bfloat16 39.5%
- 672 Ali-C137 Q2AW1M-1111 pretrained, bfloat16 39.5%
- 673 asas-ai AceGPT-v2-32B fine-tuned on domain-specific datasets, float16 39.5%
- 674 BAAI Infinity-Instruct-3M-0625-Qwen2-7B chat models, bfloat16 39.5%
- 675 cognitivecomputations dolphin-2.9.2-qwen2-7b chat models, bfloat16 39.5%
- 676 core42 jais-13b , ? 39.5%
- 677 Cran-May T.E-8.1 chat models, bfloat16 39.5%
- 678 FreedomIntelligence AceGPT-v2-32B , float16 39.5%
- 679 HeshamHaroon Testv1 chat models, float16 39.5%
- 680 hotmailuser Deeepseek-QwenSlerp4-32B base merges and moerges, bfloat16 39.5%
- 681 inceptionai jais-family-1p3b , ? 39.5%
- 682 inceptionai jais-family-2p7b , ? 39.5%
- 683 inceptionai jais-family-590m , ? 39.5%
- 684 inceptionai jais-family-6p7b , ? 39.5%
- 685 macadeliccc Samantha-Qwen-2-7B fine-tuned on domain-specific datasets, float16 39.5%
- 686 MaziyarPanahi calme-2.1-qwen2-7b fine-tuned on domain-specific datasets, bfloat16 39.5%
- 687 MaziyarPanahi calme-2.6-qwen2-7b fine-tuned on domain-specific datasets, bfloat16 39.5%
- 688 MaziyarPanahi calme-2.7-qwen2-7b fine-tuned on domain-specific datasets, bfloat16 39.5%
- 689 MBZUAI MobiLlama-1B , ? 39.5%
- 690 nitky RoguePlanet-DeepSeek-R1-Qwen-32B base merges and moerges, bfloat16 39.5%
- 691 oddadmix Arabic-Qwen2.5-3B fine-tuned on domain-specific datasets, bfloat16 39.5%
- 692 oddadmix Arabic-Qwen2.5-3B-v2 fine-tuned on domain-specific datasets, bfloat16 39.5%
- 693 oddadmix Arabic-Qwen2.5-3B-v2.1 fine-tuned on domain-specific datasets, bfloat16 39.5%
- 694 OpenBuddy openbuddy-qwen1.5-32b-v21.1-32k chat models, bfloat16 39.5%
- 695 OpenBuddy openbuddy-qwen1.5-32b-v21.2-32k chat models, bfloat16 39.5%
- 696 Orion-zhen Qwen2.5-7B-Instruct-Uncensored chat models, bfloat16 39.5%
- 697 paloalma ECE-TW3-JRGL-V2 base merges and moerges, bfloat16 39.5%
- 698 Qwen/Qwen1.5-0.5B pretrained, bfloat16 39.5%
- 699 Qwen/Qwen1.5-0.5B-Chat pretrained, bfloat16 39.5%
- 700 Qwen/Qwen1.5-32B-Chat chat models, bfloat16 39.5%
- 701 Qwen/Qwen1.5-4B pretrained, bfloat16 39.5%
- 702 Qwen/Qwen1.5-MoE-A2.7B pretrained, bfloat16 39.5%
- 703 Qwen/Qwen1.5-MoE-A2.7B-Chat pretrained, bfloat16 39.5%
- 704 Qwen/Qwen2-MoE-57B-A14B-Instruct , bfloat16 39.5%
- 705 Qwen/Qwen2.5-1.5B-Instruct chat models, bfloat16 39.5%
- 706 Qwen/Qwen2.5-Math-7B-Instruct fine-tuned on domain-specific datasets, bfloat16 39.5%
- 707 Sakalti Saka-1.5B base merges and moerges, float16 39.5%
- 708 TeetouchQQ model_mergev2 base merges and moerges, bfloat16 39.5%
- 709 VAGOsolutions SauerkrautLM-Qwen-32b chat models, bfloat16 39.5%
- 710 vilm Quyen-Pro-Max-v0.1 chat models, bfloat16 39.5%
- 711 Weyaxi Einstein-v7-Qwen2-7B chat models, bfloat16 39.5%
- 712
Qwen1.5-32B pretrained, bfloat16 39.5%
- 713
Qwen1.5-4B-Chat pretrained, bfloat16 39.5%
- 714
Qwen1.5-110B pretrained, bfloat16 39.5%
- 715
Qwen2-0.5B pretrained, bfloat16 39.5%
- 716
Qwen2-0.5B-Instruct chat models, bfloat16 39.5%
- 717
Qwen2-1.5B pretrained, bfloat16 39.5%
- 718
Qwen2-1.5B-Instruct chat models, bfloat16 39.5%
- 719
Qwen2.5-0.5B pretrained, bfloat16 39.5%
- 720 Qwen2.5-Coder-14B-Instruct fine-tuned on domain-specific datasets, bfloat16 39.5%
- 721 ai21labs Jamba-v0.1 pretrained, bfloat16 39.5%
- 722 google/recurrentgemma-2b , ? 39.5%
- 723 Slim205 Barka-2b-it fine-tuned on domain-specific datasets, bfloat16 39.5%
- 724 Qwen/Qwen1.5-110B-Chat pretrained, bfloat16 39.5%
- 725
Qwen1.5-7B pretrained, bfloat16 39.5%
- 726 Ali-C137 Q15H10M-0000 pretrained, bfloat16 39.5%
- 727 paloalma ECE-TW3-JRGL-V4 base merges and moerges, bfloat16 39.5%
- 728 Ali-C137 L3H10M-0000 pretrained, bfloat16 39.4%
- 729
Llama 3-8B pretrained, bfloat16 39.4%
- 730 princeton-nlp Llama-3-8B-ProLong-64k-Base , ? 39.4%
- 731 rombodawg rombos_Replete-Coder-Llama3-8B fine-tuned on domain-specific datasets, bfloat16 39.4%
- 732 unsloth llama-3-8b-bnb-4bit , GPTQ 39.2%
Source: Open Arabic LLM Leaderboard v1’s leaderboard
- 73.9
Qwen2.5-Math-72B-Instruct
- 63.9
Qwen2-72B
- 62.1
Qwen2.5-72B
- 61.3
DeepSeek-R1-Distill-Llama-70B
- 59.5
Falcon3-10B-Instruct
- 59.0
Falcon3-7B-Instruct
- 55.2
phi-3-medium 14B
- 52.5
Phi-3-medium-128k-instruct
- 49.6
Falcon-180B
- 47.8
Yi-1.5-9B-Chat
- 47.6
Gemma 2 27B
- 47.6
Command R (03-2024)
- 47.6
Qwen2.5-14B-Instruct-1M
- 46.5
Yi-1.5-34B
- 45.1
Qwen1.5-14B-Chat
- 44.0
Qwen2.5-14B
- 43.2
Mistral-7B-Instruct-v0.2
- 42.6
Aya Expanse 8B
- 41.9
Falcon3-3B-Instruct
- 41.5
Qwen2.5-Coder (7B)
- 41.5
Falcon3-1B-Instruct
- 41.4
Gemma 2 9B
- 40.6
Gemma 2B
- 40.5 Qwen2.5-Coder-14B
- 40.5 c4ai-command-r-08-2024
- 40.2
Gemma 7B
- 40.2
Gemma 1.1 7B IT
- 40.2
Llama 3.1-70B
- 40.1
Gemma 1.1 2B IT
- 40.1
Falcon-40B
- 40.1
Falcon-7B
- 39.9
Llama 3.2 1B
- 39.8
Llama 3.1-8B
- 39.8
DeepSeek-R1-Distill-Qwen-7B
- 39.7
Llama 3-70B
- 39.7
Qwen2.5-32B
- 39.7
Qwen1.5-7B-Chat
- 39.6
Mistral 7B v0.3
- 39.6
DeepSeek-R1-Distill-Qwen-14B
- 39.6
Qwen2.5-1.5B
- 39.6
Qwen1.5-72B
- 39.5
Qwen2-7B-Instruct
- 39.5
Qwen2.5-3B
- 39.5
Qwen2.5-7B
- 39.5
Qwen2-7B
- 39.5
Qwen1.5-14B
- 39.5
Qwen1.5-32B
- 39.5
Qwen1.5-4B-Chat
- 39.5
Qwen1.5-110B
- 39.5
Qwen2-0.5B
- 39.5
Qwen2-0.5B-Instruct
- 39.5
Qwen2-1.5B
- 39.5
Qwen2-1.5B-Instruct
- 39.5
Qwen2.5-0.5B
- 39.5 Qwen2.5-Coder-14B-Instruct
- 39.5
Qwen1.5-7B
- 39.4
Llama 3-8B
- 1
Qwen2.5-Math-72B-Instruct fine-tuned on domain-specific datasets, bfloat16 73.9%
- 2
Qwen2-72B chat models, bfloat16 63.9%
- 3
Qwen2.5-72B chat models, bfloat16 62.1%
- 4
DeepSeek-R1-Distill-Llama-70B fine-tuned on domain-specific datasets, bfloat16 61.3%
- 5
Falcon3-10B-Instruct chat models, bfloat16 59.5%
- 6
Falcon3-7B-Instruct chat models, bfloat16 59%
- 7
phi-3-medium 14B chat models, bfloat16 55.2%
- 8
Phi-3-medium-128k-instruct chat models, bfloat16 52.5%
- 9
Falcon-180B pretrained, bfloat16 49.6%
- 10
Yi-1.5-9B-Chat chat models, bfloat16 47.8%
- 11
Gemma 2 27B , ? 47.6%
- 12
Command R (03-2024) fine-tuned on domain-specific datasets, float16 47.6%
- 13
Qwen2.5-14B-Instruct-1M chat models, bfloat16 47.6%
- 14
Yi-1.5-34B pretrained, bfloat16 46.5%
- 15
Qwen1.5-14B-Chat pretrained, bfloat16 45.1%
- 16
Qwen2.5-14B pretrained, bfloat16 44%
- 17
Mistral-7B-Instruct-v0.2 chat models, bfloat16 43.2%
- 18
Aya Expanse 8B chat models, float16 42.6%
- 19
Falcon3-3B-Instruct chat models, bfloat16 41.9%
- 20
Qwen2.5-Coder (7B) pretrained, bfloat16 41.5%
- 21
Falcon3-1B-Instruct chat models, bfloat16 41.5%
- 22
Gemma 2 9B , ? 41.4%
- 23
Gemma 2B pretrained, bfloat16 40.6%
- 24 Qwen2.5-Coder-14B pretrained, bfloat16 40.5%
- 25 c4ai-command-r-08-2024 chat models, float16 40.5%
- 26
Gemma 7B pretrained, bfloat16 40.2%
- 27
Gemma 1.1 7B IT chat models, bfloat16 40.2%
- 28
Llama 3.1-70B pretrained, bfloat16 40.2%
- 29
Gemma 1.1 2B IT chat models, bfloat16 40.1%
- 30
Falcon-40B pretrained, bfloat16 40.1%
- 31
Falcon-7B pretrained, bfloat16 40.1%
- 32
Llama 3.2 1B pretrained, bfloat16 39.9%
- 33
Llama 3.1-8B pretrained, bfloat16 39.8%
- 34
DeepSeek-R1-Distill-Qwen-7B fine-tuned on domain-specific datasets, bfloat16 39.8%
- 35
Llama 3-70B pretrained, bfloat16 39.7%
- 36
Qwen2.5-32B pretrained, bfloat16 39.7%
- 37
Qwen1.5-7B-Chat pretrained, bfloat16 39.7%
- 38
Mistral 7B v0.3 pretrained, bfloat16 39.6%
- 39
DeepSeek-R1-Distill-Qwen-14B fine-tuned on domain-specific datasets, bfloat16 39.6%
- 40
Qwen2.5-1.5B pretrained, bfloat16 39.6%
- 41
Qwen1.5-72B pretrained, bfloat16 39.6%
- 42
Qwen2-7B-Instruct chat models, bfloat16 39.5%
- 43
Qwen2.5-3B pretrained, bfloat16 39.5%
- 44
Qwen2.5-7B pretrained, bfloat16 39.5%
- 45
Qwen2-7B pretrained, bfloat16 39.5%
- 46
Qwen1.5-14B pretrained, bfloat16 39.5%
- 47
Qwen1.5-32B pretrained, bfloat16 39.5%
- 48
Qwen1.5-4B-Chat pretrained, bfloat16 39.5%
- 49
Qwen1.5-110B pretrained, bfloat16 39.5%
- 50
Qwen2-0.5B pretrained, bfloat16 39.5%
- 51
Qwen2-0.5B-Instruct chat models, bfloat16 39.5%
- 52
Qwen2-1.5B pretrained, bfloat16 39.5%
- 53
Qwen2-1.5B-Instruct chat models, bfloat16 39.5%
- 54
Qwen2.5-0.5B pretrained, bfloat16 39.5%
- 55 Qwen2.5-Coder-14B-Instruct fine-tuned on domain-specific datasets, bfloat16 39.5%
- 56
Qwen1.5-7B pretrained, bfloat16 39.5%
- 57
Llama 3-8B pretrained, bfloat16 39.4%
Source: Open Arabic LLM Leaderboard v1’s leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | elmrc juhaina 8B | 92.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 2 | mssqpi Waie1 70.6B | 87.7% | chat models, bfloat16 | Official leaderboard | |
| 3 | llm-mle ara_mle_pretrained_8b | 85% | , bfloat16 | Official leaderboard | |
| 4 | llm-mle arb_mle_pretrained_8b 8B | 85% | pretrained, bfloat16 | Official leaderboard | |
| 5 | silma-ai SILMA-9B-Instruct-v1.0 9.2B | 78.9% | chat models, bfloat16 | Official leaderboard | |
| 6 | byroneverson gemma-2-27b-it-abliterated 27.2B | 77.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 7 | migtissera Tess-v2.5-Gemma-2-27B-alpha | 76.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 8 | airev-ai qwen-14b-v2 | 76.2% | , float16 | Official leaderboard | |
| 9 | elmrc juhainaG 9.2B | 75.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 10 | elmresearchcenter juhaina 9.2B | 75.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 11 | | 73.9% | fine-tuned on domain-specific datasets, bfloat16 | Sep 2024 | Official leaderboard |
| 12 | Slim205 Barka-9b-it-v02 | 73.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 13 | google/gemma-2-27b-it 27.2B | 73.1% | chat models, bfloat16 | Official leaderboard | |
| 14 | airev-ai emirati-14b-v3 14.8B | 72.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 15 | dnhkng RYS-Gemma-2-27b-it 32.9B | 72.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 16 | OpenBuddy openbuddy-deepseek-67b-v18.1-4k 67.4B | 71.6% | chat models, bfloat16 | Official leaderboard | |
| 17 | vicgalle CarbonBeagle-11B 10.7B | 71.4% | base merges and moerges, float16 | Official leaderboard | |
| 18 | MaziyarPanahi calme-2.2-qwen2-72b 72.7B | 71.2% | chat models, bfloat16 | Official leaderboard | |
| 19 | elmrc Juhaina28B | 70.2% | , ? | Official leaderboard | |
| 20 | vicgalle ConfigurableBeagle-11B 10.7B | 69.7% | chat models, float16 | Official leaderboard | |
| 21 | thariqkhalid ara_mle_sft_300_8b | 69.6% | , bfloat16 | Official leaderboard | |
| 22 | cognitivecomputations WestLake-7B-v2-laser | 69.5% | , float16 | Official leaderboard | |
| 23 | airev-ai emirati-14b-v2 14.8B | 69.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 24 | elmrc Juhaina29B 28.4B | 69% | chat models, bfloat16 | Official leaderboard | |
| 25 | Sakalti Saka-3.8B 3.8B | 69% | base merges and moerges, float16 | Official leaderboard | |
| 26 | INSAIT-Institute BgGPT-7B-Instruct-v0.2 7.3B | 68.6% | pretrained, bfloat16 | Official leaderboard | |
| 27 | Qwen/Qwen2.5-Math-72B 72.7B | 68.3% | pretrained, bfloat16 | Official leaderboard | |
| 28 | Sakalti ultiima-78B-V2 78B | 67.7% | base merges and moerges, float16 | Official leaderboard | |
| 29 | jsfs11 MixtureofMerges-MoE-4x7b-v4 24.2B | 67.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 30 | elmrc Juhaina-Instruct-v1 9.8B | 67.5% | chat models, bfloat16 | Official leaderboard | |
| 31 | dfurman CalmeRys-78B-Orpo-v0.1 78B | 67.4% | chat models, bfloat16 | Official leaderboard | |
| 32 | MaziyarPanahi Calme-4x7B-MoE-v0.2 24.2B | 67.3% | base merges and moerges, bfloat16 | Official leaderboard | |
| 33 | tiiuae/falcon-180B-chat 179.5B | 67% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 34 | dnhkng RYS-XLarge-base 78B | 67% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 35 | Sakalti ultiima-78B 78B | 66.8% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 36 | MaziyarPanahi Calme-4x7B-MoE-v0.1 24.2B | 66.6% | base merges and moerges, bfloat16 | Official leaderboard | |
| 37 | dnhkng RYS-XLarge 78B | 66.5% | chat models, bfloat16 | Official leaderboard | |
| 38 | microsoft/Phi-3.5-mini-instruct | 66.4% | , bfloat16 | Official leaderboard | |
| 39 | airev-ai Amal-70b-v5 | 66.1% | , float16 | Official leaderboard | |
| 40 | vicgalle CarbonBeagle-11B-truthy 10.7B | 66.1% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 41 | cognitivecomputations laserxtral 24.2B | 66% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 42 | MTSAIR multi_verse_model 7.2B | 66% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 43 | allknowingroger MultiverseEx26-7B-slerp 7.2B | 65.9% | base merges and moerges, bfloat16 | Official leaderboard | |
| 44 | Kukedlc NeuralSynthesis-7B-v0.1 7.2B | 65.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 45 | Kquant03 CognitiveFusion2-4x7B-BF16 24.2B | 65.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 46 | liminerity M7-7b 7.2B | 65.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 47 | Kukedlc NeuralSynthesis-7B-v0.3 7.2B | 65.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 48 | Kukedlc NeuralExperiment-7b-MagicCoder-v7.5 7.2B | 65.4% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 49 | automerger YamshadowExperiment28-7B 7.2B | 65.3% | base merges and moerges, bfloat16 | Official leaderboard | |
| 50 | Kukedlc NeuralSynthesis-7b-v0.4-slerp 7.2B | 65.2% | base merges and moerges, bfloat16 | Official leaderboard | |
| 51 | 01-ai/Yi-1.5-34B-Chat 34.4B | 65.2% | chat models, bfloat16 | Official leaderboard | |
| 52 | jondurbin bagel-dpo-34b-v0.2 34.4B | 64.6% | chat models, bfloat16 | Official leaderboard | |
| 53 | dfurman Qwen2-72B-Orpo-v0.1 72.7B | 64.4% | chat models, bfloat16 | Official leaderboard | |
| 54 | cloudyu Yi-34Bx2-MOE-200K 60.8B | 64.2% | base merges and moerges, bfloat16 | Official leaderboard | |
| 55 | | 63.9% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 56 | AALF gemma-2-27b-it-SimPO-37K-100steps 27.2B | 63.8% | chat models, bfloat16 | Official leaderboard | |
| 57 | Undi95 MG-FinalMix-72B 72.7B | 63.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 58 | ibivibiv multimaster-7b-v6 | 63.6% | , ? | Official leaderboard | |
| 59 | Weyaxi Nous-Hermes-2-SUS-Chat-34B-Slerp 34.4B | 63.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 60 | jsfs11 MixtureofMerges-MoE-4x7b-v5 24.2B | 63.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 61 | airev-ai Amal-70b-v4 | 63.5% | , float16 | Official leaderboard | |
| 62 | kevinpro Hydra-LLaMA3-8B-v0.2 | 63.4% | , ? | Official leaderboard | |
| 63 | MaziyarPanahi calme-2.1-qwen2-72b 72.7B | 63.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 64 | MaziyarPanahi Qwen2-72B-Instruct-v0.1 72.7B | 63.3% | chat models, bfloat16 | Official leaderboard | |
| 65 | altomek YiSM-34B-0rn 34.4B | 63.3% | base merges and moerges, float16 | Official leaderboard | |
| 66 | failspy Phi-3-medium-4k-instruct-abliterated-v3 14B | 63.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 67 | mssqpi ElmGemma2 10.4B | 63% | chat models, bfloat16 | Official leaderboard | |
| 68 | shadowml BeagSake-7B 7.2B | 62.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 69 | vicgalle ConfigurableSOLAR-10.7B 10.7B | 62.7% | chat models, float16 | Official leaderboard | |
| 70 | 01-ai/Yi-Coder-9B 8.8B | 62.7% | pretrained, bfloat16 | Official leaderboard | |
| 71 | abacusai Dracarys-72B-Instruct 72.7B | 62.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 72 | alpindale magnum-72b-v1 72.7B | 62.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 73 | anthracite-org magnum-v1-72b 72.7B | 62.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 74 | Sakalti ultiima-125B 125.4B | 62.4% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 75 | CombinHorizon YiSM-blossom5.1-34B-SLERP 34.4B | 62.4% | base merges and moerges, bfloat16 | Official leaderboard | |
| 76 | mistralai/Codestral-22B-v0.1 22.3B | 62.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 77 | zetasepic Qwen2.5-72B-Instruct-abliterated 72.7B | 62.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 78 | | 62.1% | chat models, bfloat16 | Sep 2024 | Official leaderboard |
| 79 | elmrc ElmJuhaina70B 70.6B | 62.1% | chat models, bfloat16 | Official leaderboard | |
| 80 | chujiezheng Smaug-34B-v0.1-ExPO 34.4B | 62% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 81 | MaziyarPanahi calme-2.1-qwen2.5-72b 72.7B | 62% | chat models, bfloat16 | Official leaderboard | |
| 82 | Sakalti ultiima-72B 72.7B | 62% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 83 | Replete-AI Replete-LLM-V2.5-Qwen-72b 72.7B | 61.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 84 | rombodawg Rombos-LLM-V2.5-Qwen-72b 72.7B | 61.9% | base merges and moerges, bfloat16 | Official leaderboard | |
| 85 | elmrc JuhainaG2 9.2B | 61.8% | chat models, bfloat16 | Official leaderboard | |
| 86 | Azure99 blossom-v5.1-34b 34.4B | 61.8% | chat models, bfloat16 | Official leaderboard | |
| 87 | sometimesanotion Lamarck-14B-v0.6 14.8B | 61.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 88 | abacusai Smaug-34B-v0.1 34.4B | 61.7% | chat models, bfloat16 | Official leaderboard | |
| 89 | meraGPT mera-mix-4x7B 24.2B | 61.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 90 | fblgit UNA-SimpleSmaug-34b-v1beta 34.4B | 61.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 91 | invalid-coder Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp 10.7B | 61.7% | base merges and moerges, float16 | Official leaderboard | |
| 92 | jeonsworld CarbonVillain-en-10.7B-v4 10.7B | 61.6% | base merges and moerges, float16 | Official leaderboard | |
| 93 | Danielbrdz Barcenas-14b-Phi-3-medium-ORPO 14B | 61.6% | chat models, float16 | Official leaderboard | |
| 94 | MaziyarPanahi calme-2.2-qwen2.5-72b 72.7B | 61.5% | chat models, bfloat16 | Official leaderboard | |
| 95 | | 61.3% | fine-tuned on domain-specific datasets, bfloat16 | Jan 2025 | Official leaderboard |
| 96 | ConvexAI Luminex-34B-v0.2 | 61.1% | , bfloat16 | Official leaderboard | |
| 97 | arcee-ai Arcee-Nova 72.7B | 61.1% | chat models, bfloat16 | Official leaderboard | |
| 98 | Sakalti SakaMoe-3x14B-Instruct 45.3B | 61% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 99 | Qwen/Qwen2.5-Coder-7B-Instruct 7.6B | 61% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 100 | cognitivecomputations dolphin-2.9.1-mixtral-1x22b 22.2B | 60.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 101 | abacusai Smaug-Qwen2-72B-Instruct 72.7B | 60.8% | chat models, bfloat16 | Official leaderboard | |
| 102 | MaziyarPanahi Topxtral-4x7B-v0.1 18.5B | 60.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 103 | kevinpro Hydra-LLaMA3-8B-v0.1 | 60.8% | , ? | Official leaderboard | |
| 104 | cloudyu TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 60.8B | 60.7% | chat models, bfloat16 | Official leaderboard | |
| 105 | VAGOsolutions SauerkrautLM-Phi-3-medium 14B | 60.7% | chat models, bfloat16 | Official leaderboard | |
| 106 | shadowml Mixolar-4x7b 36.1B | 60.7% | base merges and moerges, float16 | Official leaderboard | |
| 107 | zhengr MixTAO-7Bx2-MoE-v8.1 12.9B | 60.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 108 | kekmodel StopCarbon-10.7B-v5 10.7B | 60.6% | base merges and moerges, float16 | Official leaderboard | |
| 109 | gpt2 | 60.5% | , GPTQ | Official leaderboard | |
| 110 | freewheelin free-solar-evo-v0.11 10.7B | 60.5% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 111 | anthracite-org magnum-v3-34b 34.4B | 60.5% | chat models, bfloat16 | Official leaderboard | |
| 112 | ConvexAI Luminex-34B-v0.1 | 60.5% | , bfloat16 | Official leaderboard | |
| 113 | freewheelin free-solar-evo-v0.13 10.7B | 60.2% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 114 | kevin009 llamaRAGdrama 7.2B | 60.1% | chat models, float16 | Official leaderboard | |
| 115 | upstage SOLAR-10.7B-Instruct-v1.0 10.7B | 60% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 116 | princeton-nlp Mistral-7B-Base-SFT-IPO 7.2B | 60% | chat models, bfloat16 | Official leaderboard | |
| 117 | riotu-lab ArabianGPT-0.3B-QA | 59.9% | , ? | Official leaderboard | |
| 118 | CultriX NeuralMona_MoE-4x7B 24.2B | 59.9% | base merges and moerges, bfloat16 | Official leaderboard | |
| 119 | openchat openchat-3.6-8b-20240522 8B | 59.6% | chat models, bfloat16 | Official leaderboard | |
| 120 | cognitivecomputations dolphin-2.9.3-Yi-1.5-34B-32k | 59.6% | chat models, bfloat16 | Official leaderboard | |
| 121 | AALF gemma-2-27b-it-SimPO-37K 27.2B | 59.5% | chat models, bfloat16 | Official leaderboard | |
| 122 | | 59.5% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 123 | freewheelin free-solar-evo-v0.1 10.7B | 59.4% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 124 | sophosympatheia Midnight-Miqu-70B-v1.5 69B | 59.4% | base merges and moerges, float16 | Official leaderboard | |
| 125 | sometimesanotion Qwen2.5-14B-Vimarckoso-v3 14.8B | 59.1% | base merges and moerges, bfloat16 | Official leaderboard | |
| 126 | nbeerbower gemma2-gutenberg-27B 27.2B | 59.1% | chat models, bfloat16 | Official leaderboard | |
| 127 | | 59% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 128 | sometimesanotion Lamarck-14B-v0.7 14.8B | 59% | chat models, bfloat16 | Official leaderboard | |
| 129 | cognitivecomputations dolphin-2.9.1-yi-1.5-34b 34.4B | 58.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 130 | failspy Llama-3-70B-Instruct-abliterated-v3 70.6B | 58.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 131 | tiiuae/falcon-7b-instruct | 58.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 132 | 01-ai/Yi-Coder-9B-Chat 8.8B | 58.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 133 | royallab ZephRP-m7b 7.2B | 58.4% | base merges and moerges, bfloat16 | Official leaderboard | |
| 134 | Artples L-MChat-Small 2.8B | 58.2% | base merges and moerges, bfloat16 | Official leaderboard | |
| 135 | arcee-ai Virtuoso-Lite 10.3B | 58.2% | chat models, bfloat16 | Official leaderboard | |
| 136 | jondurbin bagel-dpo-34b-v0.5 34.4B | 58% | chat models, bfloat16 | Official leaderboard | |
| 137 | CausalLM 34b-beta 34.4B | 57.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 138 | beowolx CodeNinja-1.0-OpenChat-7B 7.2B | 57.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 139 | hotmailuser QwenSlerp2-14B 14.8B | 57.6% | base merges and moerges, bfloat16 | Official leaderboard | |
| 140 | airev-ai Amal-70b-v2 72.7B | 57.4% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 141 | elmrc JuhainaL2 9.8B | 57.4% | chat models, bfloat16 | Official leaderboard | |
| 142 | NLPark Shi-Cis-Kestrel-uncensored 140.8B | 57.3% | chat models, bfloat16 | Official leaderboard | |
| 143 | airev-ai Amal-70b-v1.1 | 57.2% | , float16 | Official leaderboard | |
| 144 | tiiuae/Falcon3-1B-Base 1.7B | 57.2% | pretrained, bfloat16 | Official leaderboard | |
| 145 | saltlux luxia-21.4b-alignment-v1.0 21.4B | 57.2% | chat models, bfloat16 | Official leaderboard | |
| 146 | princeton-nlp Mistral-7B-Base-SFT-RDPO 7.2B | 57% | chat models, bfloat16 | Official leaderboard | |
| 147 | oobabooga CodeBooga-34B-v0.1 33.7B | 57% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 148 | 01-ai/Yi-1.5-34B-Chat-16K 34.4B | 56.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 149 | RubielLabarta LogoS-7Bx2-MoE-13B-v0.2 12.9B | 56.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 150 | mlabonne NeuralMonarch-7B 7.2B | 56.6% | chat models, float16 | Official leaderboard | |
| 151 | cloudyu Mixtral_34Bx2_MoE_60B 60.8B | 56.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 152 | mlabonne AlphaMonarch-7B 7.2B | 56.3% | chat models, float16 | Official leaderboard | |
| 153 | Daemontatox Mawared_GS 9.2B | 55.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 154 | saltlux luxia-21.4b-alignment-v1.2 21.4B | 55.8% | chat models, bfloat16 | Official leaderboard | |
| 155 | dzakwan dzakwan-MoE-4x7b-Beta 24.2B | 55.7% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 156 | mlabonne Beyonder-4x7B-v3 24.2B | 55.6% | base merges and moerges, float16 | Official leaderboard | |
| 157 | tenyx Llama3-TenyxChat-70B 70.6B | 55.5% | chat models, bfloat16 | Official leaderboard | |
| 158 | princeton-nlp Mistral-7B-Base-SFT-DPO 7.2B | 55.4% | chat models, bfloat16 | Official leaderboard | |
| 159 | cloudyu Yi-34Bx2-MoE-60B-DPO 60.8B | 55.3% | chat models, bfloat16 | Official leaderboard | |
| 160 | | 55.2% | chat models, bfloat16 | Apr 2024 | Official leaderboard |
| 161 | SeaLLMs SeaLLM-7B-v2 7.4B | 55.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 162 | cloudyu Yi-34Bx2-MoE-60B 60.8B | 55% | base merges and moerges, bfloat16 | Official leaderboard | |
| 163 | byroneverson Yi-1.5-34B-Chat-abliterated 34.4B | 54.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 164 | anthracite-org magnum-v2-72b 72.7B | 54.8% | chat models, bfloat16 | Official leaderboard | |
| 165 | princeton-nlp Llama-3-Base-8B-SFT-SimPO 8B | 54.8% | chat models, bfloat16 | Official leaderboard | |
| 166 | Mihaiii Llama-3-pruned-45B-Drobeta-Turnu-Severin | 54.7% | , bfloat16 | Official leaderboard | |
| 167 | abacusai Slerp-CM-mist-dpo 7.2B | 54.4% | chat models, float16 | Official leaderboard | |
| 168 | haoranxu ALMA-13B-Pretrain | 54.3% | , ? | Official leaderboard | |
| 169 | Daemontatox Llama3.3-70B-CogniLink 70.6B | 54.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 170 | airev-ai Jais-Inception-70b-V1.1 72.7B | 54.1% | chat models, bfloat16 | Official leaderboard | |
| 171 | inceptionai jais-family-13b-chat 13B | 54% | chat models, float16 | Official leaderboard | |
| 172 | wenbopan Faro-Yi-34B-DPO 34.4B | 53.9% | chat models, bfloat16 | Official leaderboard | |
| 173 | haoranxu ALMA-13B-R 13B | 53.8% | chat models, float16 | Official leaderboard | |
| 174 | xiangxinai Xiangxin-2XL-Chat-1048k-Chinese-Llama3-70B 70.6B | 53.7% | chat models, float16 | Official leaderboard | |
| 175 | huihui-ai Qwen2.5-7B-Instruct-abliterated-v2 7.6B | 53.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 176 | VAGOsolutions Llama-3-SauerkrautLM-70b-Instruct 70.6B | 53.7% | chat models, bfloat16 | Official leaderboard | |
| 177 | mssqpi ALQLora2 | 53.6% | , ? | Official leaderboard | |
| 178 | MaziyarPanahi calme-2.4-llama3-70b | 53.5% | chat models, bfloat16 | Official leaderboard | |
| 179 | mmnga Llama-3-70B-japanese-suzume-vector-v0.1 70.6B | 53.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 180 | meta-llama/Meta-Llama-3-70B-Instruct 70.6B | 53.4% | chat models, bfloat16 | Official leaderboard | |
| 181 | MaziyarPanahi calme-2.2-llama3-70b 70.6B | 53.3% | chat models, bfloat16 | Official leaderboard | |
| 182 | MaziyarPanahi Llama-3-70B-Instruct-DPO-v0.2 70.6B | 53.3% | chat models, bfloat16 | Official leaderboard | |
| 183 | princeton-nlp Mistral-7B-Base-SFT-SimPO 7.2B | 53.3% | chat models, bfloat16 | Official leaderboard | |
| 184 | wenbopan Faro-Yi-9B-DPO | 53.2% | , bfloat16 | Official leaderboard | |
| 185 | nvidia Llama3-ChatQA-1.5-8B 8B | 53.1% | chat models, float16 | Official leaderboard | |
| 186 | vicgalle ConfigurableHermes-7B 7.2B | 53% | chat models, float16 | Official leaderboard | |
| 187 | tanliboy lambda-qwen2.5-14b-dpo-test 14.8B | 52.8% | chat models, bfloat16 | Official leaderboard | |
| 188 | Weyaxi Bagel-Hermes-34B-Slerp 34.4B | 52.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 189 | Qwen/Qwen1.5-1.8B 1.8B | 52.7% | pretrained, bfloat16 | Official leaderboard | |
| 190 | | 52.5% | chat models, bfloat16 | May 2024 | Official leaderboard |
| 191 | OpenBuddy openbuddy-yi1.5-34b-v21.3-32k 34.4B | 52.5% | chat models, bfloat16 | Official leaderboard | |
| 192 | MaziyarPanahi calme-2.3-llama3-70b 70.6B | 52.5% | chat models, bfloat16 | Official leaderboard | |
| 193 | airev-ai Amal-75b-v3 | 52.5% | , float16 | Official leaderboard | |
| 194 | riotu-lab ArabianGPT-01B | 52.5% | , ? | Official leaderboard | |
| 195 | MaziyarPanahi calme-2.2-llama3.1-70b 70.6B | 52.3% | chat models, bfloat16 | Official leaderboard | |
| 196 | byroneverson Yi-1.5-9B-Chat-abliterated 8.8B | 52.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 197 | abacusai Smaug-Llama-3-70B-Instruct-32K 70.6B | 52% | chat models, bfloat16 | Official leaderboard | |
| 198 | Sakalti ultiima-14B 14.8B | 52% | base merges and moerges, float16 | Official leaderboard | |
| 199 | huihui-ai Qwen2.5-32B-Instruct-abliterated 32.8B | 52% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 200 | airev-ai qwen-14b-v1 | 51.9% | , float16 | Official leaderboard | |
| 201 | v000000 Qwen2.5-Lumen-14B 14.8B | 51.8% | chat models, bfloat16 | Official leaderboard | |
| 202 | NousResearch Hermes-3-Llama-3.1-70B 70.6B | 51.8% | chat models, bfloat16 | Official leaderboard | |
| 203 | Replete-AI Replete-LLM-V2.5-Qwen-14b 14.8B | 51.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 204 | Qwen/Qwen2.5-14B-Instruct 14.8B | 51.8% | chat models, bfloat16 | Official leaderboard | |
| 205 | princeton-nlp Llama-3-Base-8B-SFT-IPO 8B | 51.7% | chat models, bfloat16 | Official leaderboard | |
| 206 | Nexusflow Athene-70B | 51.6% | , bfloat16 | Official leaderboard | |
| 207 | haoranxu ALMA-7B-R | 51.5% | , float16 | Official leaderboard | |
| 208 | Lambent qwen2.5-reinstruct-alternate-lumen-14B 14.8B | 51.4% | base merges and moerges, bfloat16 | Official leaderboard | |
| 209 | v000000 Qwen2.5-14B-Gutenberg-1e-Delta 14.8B | 51.4% | chat models, bfloat16 | Official leaderboard | |
| 210 | recoilme recoilme-gemma-2-9B-v0.4 10.2B | 51.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 211 | v000000 Qwen2.5-14B-Gutenberg-Instruct-Slerpeno 14.8B | 51.1% | base merges and moerges, bfloat16 | Official leaderboard | |
| 212 | dnhkng RYS-Llama3.1-Large 81.7B | 51.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 213 | rombodawg Rombos-LLM-V2.6-Nemotron-70b 70.6B | 51% | base merges and moerges, bfloat16 | Official leaderboard | |
| 214 | yunconglong Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 12.9B | 51% | chat models, bfloat16 | Official leaderboard | |
| 215 | meta-llama/Meta-Llama-3.1-70B-Instruct 70.6B | 50.9% | chat models, bfloat16 | Official leaderboard | |
| 216 | VAGOsolutions Llama-3.1-SauerkrautLM-70b-Instruct 70.6B | 50.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 217 | nvidia Llama-3.1-Nemotron-70B-Instruct-HF 70.6B | 50.4% | chat models, bfloat16 | Official leaderboard | |
| 218 | NousResearch Nous-Hermes-2-SOLAR-10.7B 10.7B | 50.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 219 | OpenBuddy openbuddy-zero-56b-v21.2-32k 56.7B | 50.3% | chat models, bfloat16 | Official leaderboard | |
| 220 | princeton-nlp Mistral-7B-Instruct-RRHF 7.2B | 50.3% | chat models, bfloat16 | Official leaderboard | |
| 221 | jpacifico Chocolatine-14B-Instruct-DPO-v1.2 14B | 50.2% | chat models, float16 | Official leaderboard | |
| 222 | princeton-nlp Llama-3-Base-8B-SFT-RDPO 8B | 50.2% | chat models, bfloat16 | Official leaderboard | |
| 223 | abhishek autotrain-llama3-70b-orpo-v1 70.6B | 50.1% | chat models, float16 | Official leaderboard | |
| 224 | allknowingroger Ph3della5-14B 14B | 50.1% | base merges and moerges, float16 | Official leaderboard | |
| 225 | wenbopan Faro-Yi-34B 34.4B | 50% | chat models, bfloat16 | Official leaderboard | |
| 226 | MaziyarPanahi calme-2.3-llama3.1-70b 70.6B | 50% | chat models, bfloat16 | Official leaderboard | |
| 227 | 01-ai/Yi-1.5-34B-32K 34.4B | 49.9% | pretrained, bfloat16 | Official leaderboard | |
| 228 | jpacifico Chocolatine-14B-Instruct-4k-DPO 14B | 49.7% | chat models, float16 | Official leaderboard | |
| 229 | Magpie-Align Llama-3-8B-Magpie-Align-v0.3 8B | 49.7% | chat models, bfloat16 | Official leaderboard | |
| 230 | | 49.6% | pretrained, bfloat16 | Sep 2023 | Official leaderboard |
| 231 | paloalma ECE-TW3-JRGL-V1 69B | 49.4% | base merges and moerges, float16 | Official leaderboard | |
| 232 | byroneverson Yi-1.5-9B-Chat-16K-abliterated 8.8B | 49.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 233 | BAAI Gemma2-9B-IT-Simpo-Infinity-Preference 9.2B | 49.3% | chat models, bfloat16 | Official leaderboard | |
| 234 | yunconglong MoE_13B_DPO 12.9B | 49.2% | chat models, bfloat16 | Official leaderboard | |
| 235 | elmrc JuhainaL 8B | 49.1% | chat models, bfloat16 | Official leaderboard | |
| 236 | anthracite-org magnum-v3-27b-kto | 49.1% | , ? | Official leaderboard | |
| 237 | google/gemma-2-9b-it 9.2B | 49% | chat models, bfloat16 | Official leaderboard | |
| 238 | UCLA-AGI Gemma-2-9B-It-SPPO-Iter1 9.2B | 48.8% | chat models, bfloat16 | Official leaderboard | |
| 239 | Qwen/Qwen1.5-1.8B-Chat 1.8B | 48.6% | pretrained, bfloat16 | Official leaderboard | |
| 240 | rombodawg Rombos-LLM-V2.6-Qwen-14b 14.8B | 48.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 241 | airev-ai Jais-Inception-70b-V1.2 | 48.3% | , float16 | Official leaderboard | |
| 242 | yunconglong DARE_TIES_13B 12.9B | 48.2% | base merges and moerges, bfloat16 | Official leaderboard | |
| 243 | lightblue suzume-llama-3-8B-multilingual-orpo-borda-top75 8B | 48% | chat models, bfloat16 | Official leaderboard | |
| 244 | failspy llama-3-70B-Instruct-abliterated 70.6B | 48% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 245 | lightblue suzume-llama-3-8B-multilingual-orpo-borda-half 8B | 48% | chat models, bfloat16 | Official leaderboard | |
| 246 | vicgalle Configurable-Mistral-7B 7.2B | 47.9% | chat models, float16 | Official leaderboard | |
| 247 | | 47.8% | chat models, bfloat16 | May 2024 | Official leaderboard |
| 248 | princeton-nlp Llama-3-Base-8B-SFT-DPO 8B | 47.8% | chat models, bfloat16 | Official leaderboard | |
| 249 | | 47.6% | , ? | Jun 2024 | Official leaderboard |
| 250 | | 47.6% | fine-tuned on domain-specific datasets, float16 | Mar 2024 | Official leaderboard |
| 251 | | 47.6% | chat models, bfloat16 | Jan 2025 | Official leaderboard |
| 252 | UCLA-AGI Gemma-2-9B-It-SPPO-Iter2 9.2B | 47.5% | chat models, bfloat16 | Official leaderboard | |
| 253 | princeton-nlp Llama-3-Base-8B-SFT-KTO 8B | 47.5% | chat models, bfloat16 | Official leaderboard | |
| 254 | shenzhi-wang Llama3-70B-Chinese-Chat 70.6B | 47.4% | chat models, bfloat16 | Official leaderboard | |
| 255 | princeton-nlp Llama-3-Instruct-8B-RDPO-v0.2 8B | 47.3% | chat models, bfloat16 | Official leaderboard | |
| 256 | migtissera Tess-v2.5-Phi-3-medium-128k-14B 14B | 47.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 257 | Ashmal MBZUAI-oryx 46.9B | 47.3% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 258 | 01-ai/Yi-1.5-9B-Chat-16K 8.8B | 47.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 259 | airev-ai Jais-Inception-70b-V1.2.2 | 47.1% | , float16 | Official leaderboard | |
| 260 | princeton-nlp Llama-3-Instruct-8B-DPO-v0.2 8B | 47% | chat models, bfloat16 | Official leaderboard | |
| 261 | UCLA-AGI Gemma-2-9B-It-SPPO-Iter3 9.2B | 47% | chat models, bfloat16 | Official leaderboard | |
| 262 | abacusai Smaug-Llama-3-70B-Instruct 70.6B | 47% | chat models, bfloat16 | Official leaderboard | |
| 263 | FreedomIntelligence AceGPT-7B-chat | 46.8% | chat models, float16 | Official leaderboard | |
| 264 | TareksLab Thalassic-Alpha-LLaMa-70B 70.6B | 46.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 265 | princeton-nlp Mistral-7B-Instruct-SimPO 7.2B | 46.7% | chat models, bfloat16 | Official leaderboard | |
| 266 | Joseph717171 Llama-3.1-SuperNova-8B-Lite_TIES_with_Base 8B | 46.6% | base merges and moerges, bfloat16 | Official leaderboard | |
| 267 | EpistemeAI Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R2 8B | 46.5% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 268 | | 46.5% | pretrained, bfloat16 | May 2024 | Official leaderboard |
| 269 | paulml ECE-ILAB-Q1 72.7B | 46.4% | base merges and moerges, bfloat16 | Official leaderboard | |
| 270 | vicgalle Configurable-Yi-1.5-9B-Chat 8.8B | 46.4% | chat models, float16 | Official leaderboard | |
| 271 | MTSAIR MultiVerse_70B 72.3B | 46.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 272 | airev-ai Jais-Inception-7b-V0.2 7.6B | 46.1% | chat models, bfloat16 | Official leaderboard | |
| 273 | EpistemeAI Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code | 46% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 274 | Omartificial-Intelligence-Space Arabic-llama3.1-16bit-FT | 46% | , bfloat16 | Official leaderboard | |
| 275 | CohereForAI/aya-23-8B 8B | 46% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 276 | Omartificial-Intelligence-Space al-baka-llama3-8b-experimental | 45.9% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 277 | paloalma TW3-JRGL-v2 72.3B | 45.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 278 | freewheelin free-evo-qwen72b-v0.8-re 72.3B | 45.7% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 279 | tiiuae/falcon-40b-instruct | 45.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 280 | SenseLLM ReflectionCoder-DS-33B 33.3B | 45.5% | chat models, bfloat16 | Official leaderboard | |
| 281 | davidkim205 Rhea-72b-v0.5 72.3B | 45.4% | chat models, bfloat16 | Official leaderboard | |
| 282 | princeton-nlp Llama-3-Instruct-8B-SimPO-v0.2 8B | 45.3% | chat models, bfloat16 | Official leaderboard | |
| 283 | Ashmal MBZUAI-ORYX-new | 45.2% | , float16 | Official leaderboard | |
| 284 | chujiezheng Mistral7B-PairRM-SPPO-ExPO 7.2B | 45.1% | chat models, bfloat16 | Official leaderboard | |
| 285 | | 45.1% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 286 | Artples L-MChat-7b 7.2B | 44.9% | base merges and moerges, bfloat16 | Official leaderboard | |
| 287 | upstage SOLAR-10.7B-v1.0 10.7B | 44.9% | pretrained, float16 | Official leaderboard | |
| 288 | UCLA-AGI Mistral7B-PairRM-SPPO 7.2B | 44.9% | chat models, bfloat16 | Official leaderboard | |
| 289 | UCLA-AGI Mistral7B-PairRM-SPPO-Iter1 7.2B | 44.8% | chat models, bfloat16 | Official leaderboard | |
| 290 | princeton-nlp Mistral-7B-Base-SFT-SLiC-HF 7.2B | 44.8% | chat models, bfloat16 | Official leaderboard | |
| 291 | RDson WomboCombo-R1-Coder-14B-Preview 14.8B | 44.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 292 | princeton-nlp Llama-3-Base-8B-SFT-SLiC-HF 8B | 44.6% | chat models, bfloat16 | Official leaderboard | |
| 293 | Syed-Hasan-8503 Phi-3-mini-4K-instruct-cpo-simpo 3.8B | 44.5% | chat models, bfloat16 | Official leaderboard | |
| 294 | OpenBuddy openbuddy-llama3.1-8b-v22.3-131k 8B | 44.5% | chat models, bfloat16 | Official leaderboard | |
| 295 | UCLA-AGI Mistral7B-PairRM-SPPO-Iter2 7.2B | 44.4% | chat models, bfloat16 | Official leaderboard | |
| 296 | cognitivecomputations dolphin-2.6-mixtral-8x7b | 44.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 297 | riotu-lab ArabianGPT-03B | 44.2% | , ? | Official leaderboard | |
| 298 | TIGER-Lab MAmmoTH2-8B-Plus 8B | 44.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 299 | migtissera Tess-M-v1.3 | 44.2% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 300 | 01-ai/Yi-9B-200K 8.8B | 44.2% | pretrained, bfloat16 | Official leaderboard | |
| 301 | jondurbin airoboros-dpo-70b-3.3 70.6B | 44.2% | chat models, bfloat16 | Official leaderboard | |
| 302 | openchat openchat-3.5-0106-gemma 8.5B | 44.2% | chat models, bfloat16 | Official leaderboard | |
| 303 | inceptionai jais-adapted-13b-chat 13.3B | 44.1% | chat models, float16 | Official leaderboard | |
| 304 | cognitivecomputations dolphin-2.9.3-mistral-nemo-12b 12.3B | 44% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 305 | FreedomIntelligence AceGPT-13B-chat | 44% | chat models, float16 | Official leaderboard | |
| 306 | | 44% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 307 | princeton-nlp Mistral-7B-Instruct-DPO 7.2B | 43.8% | chat models, bfloat16 | Official leaderboard | |
| 308 | FreedomIntelligence AceGPT-7B 7B | 43.8% | pretrained, float16 | Official leaderboard | |
| 309 | sajaw llama-2-7b-RandomGPT-5K-ar | 43.7% | , bfloat16 | Official leaderboard | |
| 310 | lemon-mint gemma-ko-7b-instruct-v0.62 8.5B | 43.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 311 | meta-llama/Llama-2-13b-hf 13B | 43.6% | pretrained, float16 | Official leaderboard | |
| 312 | jondurbin airoboros-70b-3.3 70.6B | 43.6% | chat models, bfloat16 | Official leaderboard | |
| 313 | princeton-nlp Mistral-7B-Base-SFT-CPO 7.2B | 43.6% | chat models, bfloat16 | Official leaderboard | |
| 314 | UCLA-AGI Mistral7B-PairRM-SPPO-Iter3 7.2B | 43.5% | chat models, bfloat16 | Official leaderboard | |
| 315 | cstr llama3-8b-spaetzle-v37 8B | 43.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 316 | elmrc JuhainaG9B 9.2B | 43.5% | chat models, bfloat16 | Official leaderboard | |
| 317 | EpistemeAI Fireball-Alpaca-Llama-3.1-8B-Philos-DPO-200 8B | 43.5% | chat models, float16 | Official leaderboard | |
| 318 | arcee-ai Llama-3.1-SuperNova-Lite 8B | 43.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 319 | princeton-nlp gemma-2-9b-it-SimPO 9.2B | 43.5% | chat models, bfloat16 | Official leaderboard | |
| 320 | MaziyarPanahi Llama-3-8B-Instruct-v0.10 8B | 43.4% | chat models, bfloat16 | Official leaderboard | |
| 321 | leafspark Llama-3.1-8B-MultiReflection-Instruct 8B | 43.4% | chat models, float16 | Official leaderboard | |
| 322 | princeton-nlp Llama-3-Base-8B-SFT-ORPO 8B | 43.4% | chat models, bfloat16 | Official leaderboard | |
| 323 | princeton-nlp Mistral-7B-Instruct-RDPO 7.2B | 43.3% | chat models, bfloat16 | Official leaderboard | |
| 324 | migtissera Tess-v2.5.2-Qwen2-72B | 43.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 325 | meta-llama/Llama-2-70b-hf 69B | 43.3% | pretrained, float16 | Official leaderboard | |
| 326 | abhishek autotrain-llama3-70b-orpo-v2 70.6B | 43.2% | chat models, float16 | Official leaderboard | |
| 327 | DeepMount00 Llama-3.1-8b-Ita 8B | 43.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 328 | | 43.2% | chat models, bfloat16 | Dec 2023 | Official leaderboard |
| 329 | EpistemeAI Fireball-Alpaca-Llama3.1.08-8B-Philos-C-R1-KTO-beta 8B | 43.2% | chat models, float16 | Official leaderboard | |
| 330 | EpistemeAI Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-beta | 43.1% | chat models, float16 | Official leaderboard | |
| 331 | gbueno86 Meta-LLama-3-Cat-Smaug-LLama-70b 70.6B | 43.1% | base merges and moerges, bfloat16 | Official leaderboard | |
| 332 | mlabonne NeuralDaredevil-8B-abliterated 8B | 43.1% | chat models, float16 | Official leaderboard | |
| 333 | arcee-ai Virtuoso-Small 14.8B | 43.1% | chat models, bfloat16 | Official leaderboard | |
| 334 | cognitivecomputations dolphin-2.9.1-yi-1.5-9b 8.8B | 43.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 335 | airev-ai Jais-Inception-7b-V0.1 7.6B | 43% | chat models, bfloat16 | Official leaderboard | |
| 336 | failspy Meta-Llama-3-70B-Instruct-abliterated-v3.5 70.6B | 43% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 337 | Isaak-Carter Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 7.6B | 43% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 338 | abacusai Smaug-72B-v0.1 72.3B | 43% | chat models, bfloat16 | Official leaderboard | |
| 339 | cognitivecomputations dolphin-2.9.1-llama-3-70b 70.6B | 43% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 340 | inceptionai jais-family-30b-16k-chat 30B | 43% | chat models, float16 | Official leaderboard | |
| 341 | abacusai Smaug-Mixtral-v0.1 | 43% | , ? | Official leaderboard | |
| 342 | BAAI Infinity-Instruct-3M-0625-Yi-1.5-9B | 42.9% | chat models, bfloat16 | Official leaderboard | |
| 343 | recoilme Gemma-2-Ataraxy-Gemmasutra-9B-slerp 10.2B | 42.9% | base merges and moerges, bfloat16 | Official leaderboard | |
| 344 | EpistemeAI2 Fireball-Alpaca-Llama-3.1-8B-Instruct-KTO-beta | 42.9% | chat models, float16 | Official leaderboard | |
| 345 | freewheelin free-llama3-dpo-v0.2 8B | 42.8% | chat models, bfloat16 | Official leaderboard | |
| 346 | arcee-ai Llama-Spark | 42.8% | , ? | Official leaderboard | |
| 347 | meta-llama/Meta-Llama-3.1-8B-Instruct 8B | 42.8% | chat models, bfloat16 | Official leaderboard | |
| 348 | ClusterlabAi GemmAr-7B-v1 8.5B | 42.8% | chat models, float16 | Official leaderboard | |
| 349 | AXCXEPT EZO-Qwen2.5-72B-Instruct 72.7B | 42.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 350 | paloalma Le_Triomphant-ECE-TW3 72.3B | 42.6% | base merges and moerges, bfloat16 | Official leaderboard | |
| 351 | cognitivecomputations dolphin-2.9.3-llama-3-8b 8B | 42.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 352 | | 42.6% | chat models, float16 | Oct 2024 | Official leaderboard |
| 353 | VAGOsolutions Llama-3.1-SauerkrautLM-8b-Instruct 8B | 42.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 354 | Steelskull L3-MS-Astoria-70b 70.6B | 42.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 355 | tanliboy lambda-qwen2.5-32b-dpo-test 32.8B | 42.5% | chat models, bfloat16 | Official leaderboard | |
| 356 | openchat openchat-3.5-0106 7.2B | 42.4% | chat models, bfloat16 | Official leaderboard | |
| 357 | vicgalle Configurable-Llama-3.1-8B-Instruct 8B | 42.4% | chat models, float16 | Official leaderboard | |
| 358 | pankajmathur orca_mini_v7_72b | 42.4% | chat models, bfloat16 | Official leaderboard | |
| 359 | MaziyarPanahi Llama-3-8B-Instruct-v0.9 8B | 42.4% | chat models, bfloat16 | Official leaderboard | |
| 360 | Qwen/Qwen2.5-Math-7B 7.6B | 42.4% | pretrained, bfloat16 | Official leaderboard | |
| 361 | princeton-nlp Mistral-7B-Instruct-KTO 7.2B | 42.4% | chat models, bfloat16 | Official leaderboard | |
| 362 | inceptionai jais-adapted-70b-chat 69.5B | 42.4% | chat models, float16 | Official leaderboard | |
| 363 | bunnycore HyperLlama-3.1-8B 8B | 42.3% | base merges and moerges, bfloat16 | Official leaderboard | |
| 364 | brucethemoose Yi-34B-200K-DARE-merge-v7 34.4B | 42.3% | base merges and moerges, bfloat16 | Official leaderboard | |
| 365 | cognitivecomputations dolphin-2.9.2-Phi-3-Medium | 42.2% | chat models, bfloat16 | Official leaderboard | |
| 366 | anthracite-org magnum-v3-9b-customgemma2 9.2B | 42.2% | chat models, bfloat16 | Official leaderboard | |
| 367 | mssqpi G3 9.2B | 42.2% | chat models, bfloat16 | Official leaderboard | |
| 368 | princeton-nlp Llama-3-Instruct-8B-IPO-v0.2 8B | 42.2% | chat models, bfloat16 | Official leaderboard | |
| 369 | silma-ai SILMA-9B-Instruct-v0.1 9.2B | 42.2% | chat models, bfloat16 | Official leaderboard | |
| 370 | silma-ai SILMA-9B-Instruct-v0.1.0 9.2B | 42.2% | chat models, bfloat16 | Official leaderboard | |
| 371 | silma-ai SILMA-9B-Instruct-v0.1.1 9.2B | 42.2% | pretrained, bfloat16 | Official leaderboard | |
| 372 | RLHFlow LLaMA3-iterative-DPO-final 8B | 42.1% | chat models, bfloat16 | Official leaderboard | |
| 373 | Orenguteng Llama-3.1-8B-Lexi-Uncensored-V2 8B | 42.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 374 | lightblue suzume-llama-3-8B-multilingual-orpo-borda-full 8B | 42% | chat models, bfloat16 | Official leaderboard | |
| 375 | mlabonne Daredevil-8B-abliterated 8B | 42% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 376 | princeton-nlp Llama-3-Instruct-8B-KTO-v0.2 8B | 42% | chat models, bfloat16 | Official leaderboard | |
| 377 | | 41.9% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 378 | BAAI Infinity-Instruct-3M-0613-Mistral-7B 7.2B | 41.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 379 | deepseek-ai/DeepSeek-R1-Distill-Llama-8B 8B | 41.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 380 | cognitivecomputations openchat-3.5-0106-laser 7.2B | 41.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 381 | dnhkng RYS-Llama-3.1-8B-Instruct 8.7B | 41.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 382 | Magpie-Align Llama-3-8B-Magpie-Align-SFT-v0.3 8B | 41.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 383 | Orenguteng Llama-3.1-8B-Lexi-Uncensored 8B | 41.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 384 | wenbopan Faro-Yi-9B 8.8B | 41.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 385 | rombodawg Everyone-Coder-4x7b-Base | 41.8% | , bfloat16 | Official leaderboard | |
| 386 | axolotl-ai-co romulus-mistral-nemo-12b-simpo 12.3B | 41.8% | chat models, bfloat16 | Official leaderboard | |
| 387 | cognitivecomputations dolphin-2.9.2-Phi-3-Medium-abliterated 14B | 41.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 388 | tiiuae/falcon-11B 11.1B | 41.7% | pretrained, bfloat16 | Official leaderboard | |
| 389 | grimjim Llama-3.1-8B-Instruct-abliterated_via_adapter 8B | 41.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 390 | SeaLLMs SeaLLM-7B-v2.5 8.5B | 41.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 391 | vicgalle Configurable-Hermes-2-Pro-Llama-3-8B 8B | 41.7% | chat models, float16 | Official leaderboard | |
| 392 | CohereForAI/aya-23-35B 35B | 41.6% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 393 | FreedomIntelligence AceGPT-13B 13B | 41.6% | pretrained, float16 | Official leaderboard | |
| 394 | uukuguy zephyr-7b-alpha-dare-0.85 | 41.6% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 395 | princeton-nlp gemma-2-9b-it-DPO | 41.6% | , bfloat16 | Official leaderboard | |
| 396 | tiiuae/Falcon3-7B-Base 7.5B | 41.6% | pretrained, bfloat16 | Official leaderboard | |
| 397 | cognitivecomputations dolphin-2.9.3-mistral-7B-32k 7.3B | 41.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 398 | | 41.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 399 | | 41.5% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 400 | uygarkurt llama-3-merged-linear 8B | 41.5% | base merges and moerges, float16 | Official leaderboard | |
| 401 | Magpie-Align MagpieLM-8B-Chat-v0.1 8B | 41.4% | chat models, bfloat16 | Official leaderboard | |
| 402 | | 41.4% | , ? | Jun 2024 | Official leaderboard |
| 403 | recoilme recoilme-gemma-2-9B-v0.2 10.2B | 41.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 404 | VAGOsolutions Llama-3-SauerkrautLM-8b-Instruct 8B | 41.4% | chat models, bfloat16 | Official leaderboard | |
| 405 | princeton-nlp Llama-3-Instruct-8B-RDPO 8B | 41.4% | chat models, bfloat16 | Official leaderboard | |
| 406 | DeepMount00 Llama-3-8b-Ita 8B | 41.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 407 | FiditeNemini Unhinged-Qwen2-72B 72.7B | 41.3% | base merges and moerges, bfloat16 | Official leaderboard | |
| 408 | MaziyarPanahi Llama-3-8B-Instruct-v0.8 8B | 41.3% | chat models, bfloat16 | Official leaderboard | |
| 409 | princeton-nlp Llama-3-Instruct-8B-DPO 8B | 41.3% | chat models, bfloat16 | Official leaderboard | |
| 410 | princeton-nlp Llama-3-Instruct-8B-CPO-v0.2 8B | 41.3% | chat models, bfloat16 | Official leaderboard | |
| 411 | vicgalle Configurable-Janus-7B 7.2B | 41.2% | chat models, float16 | Official leaderboard | |
| 412 | jondurbin bagel-8b-v1.0 8B | 41.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 413 | Isaak-Carter Josiefied-Qwen2.5-7B-Instruct-abliterated 7.6B | 41.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 414 | TheDrummer Gemmasutra-9B-v1 10.2B | 41.1% | base merges and moerges, bfloat16 | Official leaderboard | |
| 415 | princeton-nlp Mistral-7B-Instruct-IPO 7.2B | 41% | chat models, bfloat16 | Official leaderboard | |
| 416 | amazon MegaBeam-Mistral-7B-300k 7.2B | 41% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 417 | Dampfinchen Llama-3.1-8B-Ultra-Instruct 8B | 41% | base merges and moerges, bfloat16 | Official leaderboard | |
| 418 | VAGOsolutions SauerkrautLM-Gemma-7b 8.5B | 41% | chat models, bfloat16 | Official leaderboard | |
| 419 | BAAI Infinity-Instruct-3M-0625-Llama3-8B 8B | 41% | chat models, bfloat16 | Official leaderboard | |
| 420 | migtissera Tess-3-Mistral-Nemo-12B 12.3B | 40.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 421 | NotAiLOL Yi-1.5-dolphin-9B 8.8B | 40.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 422 | princeton-nlp Llama-3-Base-8B-SFT-RRHF 8B | 40.9% | chat models, bfloat16 | Official leaderboard | |
| 423 | princeton-nlp Llama-3-Base-8B-SFT 8B | 40.9% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 424 | inceptionai jais-adapted-70b 69.5B | 40.9% | chat models, float16 | Official leaderboard | |
| 425 | uukuguy speechless-zephyr-code-functionary-7b 7.2B | 40.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 426 | airev-ai Jais-Inception-70b | 40.8% | , bfloat16 | Official leaderboard | |
| 427 | anthracite-org magnum-v3-9b-chatml 9.2B | 40.8% | chat models, bfloat16 | Official leaderboard | |
| 428 | 618AI dictalm2-it-qa-fine-tune | 40.8% | , bfloat16 | Official leaderboard | |
| 429 | TIGER-Lab MAmmoTH2-7B-Plus 7.2B | 40.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 430 | migtissera Tess-3-Llama-3.1-70B | 40.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 431 | OpenBuddy openbuddy-qwen2.5llamaify-14b-v23.1-200k 14.8B | 40.7% | chat models, bfloat16 | Official leaderboard | |
| 432 | Eurdem Defne-llama3.1-8B 8B | 40.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 433 | princeton-nlp Llama-3-Instruct-8B-KTO 8B | 40.7% | chat models, bfloat16 | Official leaderboard | |
| 434 | Replete-AI Replete-LLM-V2.5-Qwen-32b 32.8B | 40.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 435 | ValiantLabs Llama3.1-8B-ShiningValiant2 | 40.7% | , ? | Official leaderboard | |
| 436 | NousResearch Hermes-2-Theta-Llama-3-8B 8B | 40.7% | chat models, bfloat16 | Official leaderboard | |
| 437 | Qwen/Qwen2.5-32B-Instruct 32.8B | 40.7% | chat models, bfloat16 | Official leaderboard | |
| 438 | v000000 L3.1-Niitorm-8B-DPO-t0.0001 8B | 40.6% | chat models, float16 | Official leaderboard | |
| 439 | meta-llama/Llama-3.2-3B-Instruct 3.2B | 40.6% | chat models, bfloat16 | Official leaderboard | |
| 440 | princeton-nlp Llama-3-Base-8B-SFT-CPO 8B | 40.6% | chat models, bfloat16 | Official leaderboard | |
| 441 | core42 jais-13b-chat | 40.6% | , ? | Official leaderboard | |
| 442 | princeton-nlp Llama-3-Instruct-8B-SimPO 8B | 40.6% | chat models, bfloat16 | Official leaderboard | |
| 443 | | 40.6% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 444 | core42 jais-30b-chat-v1 | 40.6% | , ? | Official leaderboard | |
| 445 | FreedomIntelligence AceGPT-v2-8B-Chat 8B | 40.6% | chat models, float16 | Official leaderboard | |
| 446 | inceptionai jais-family-6p7b-chat | 40.6% | , ? | Official leaderboard | |
| 447 | princeton-nlp Llama-3-Instruct-8B-ORPO-v0.2 8B | 40.6% | chat models, bfloat16 | Official leaderboard | |
| 448 | silma-ai SILMA-Kashif-2B-Instruct-v1.0 2.6B | 40.6% | chat models, bfloat16 | Official leaderboard | |
| 449 | Sakalti ultiima-32B 32.8B | 40.5% | base merges and moerges, float16 | Official leaderboard | |
| 450 | Qwen2.5-Coder-14B | 40.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 451 | uukuguy speechless-code-mistral-7b-v1.0 | 40.5% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 452 | c4ai-command-r-08-2024 | 40.5% | chat models, float16 | Aug 2024 | Official leaderboard |
| 453 | inceptionai jais-adapted-7b-chat | 40.5% | , ? | Official leaderboard | |
| 454 | TIGER-Lab MAmmoTH2-8x7B-Plus 46.7B | 40.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 455 | cognitivecomputations dolphin-2.9.2-qwen2-72b 72.7B | 40.4% | chat models, bfloat16 | Official leaderboard | |
| 456 | BAAI OPI-Llama-3.1-8B-Instruct 8B | 40.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 457 | Ba2han QwQenSeek-coder 32.8B | 40.4% | base merges and moerges, bfloat16 | Official leaderboard | |
| 458 | cognitivecomputations dolphin-2.9.1-llama-3-8b 8B | 40.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 459 | cognitivecomputations Llama-3-8B-Instruct-abliterated-v2 8B | 40.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 460 | Ali-C137 Ge1H10M-0000 8.5B | 40.4% | pretrained, bfloat16 | Official leaderboard | |
| 461 | inceptionai jais-family-2p7b-chat | 40.4% | , ? | Official leaderboard | |
| 462 | mlabonne ChimeraLlama-3-8B-v2 8B | 40.4% | base merges and moerges, float16 | Official leaderboard | |
| 463 | failspy Smaug-Llama-3-70B-Instruct-abliterated-v3 70.6B | 40.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 464 | maldv Qwenstein2.5-32B-Instruct 32.8B | 40.4% | base merges and moerges, bfloat16 | Official leaderboard | |
| 465 | gbueno86 Meta-LLama-3-Cat-A-LLama-70b 70.6B | 40.4% | base merges and moerges, bfloat16 | Official leaderboard | |
| 466 | princeton-nlp Llama-3-Instruct-8B-RRHF-v0.2 8B | 40.4% | chat models, bfloat16 | Official leaderboard | |
| 467 | princeton-nlp Llama-3-Instruct-8B-SLiC-HF-v0.2 8B | 40.4% | chat models, bfloat16 | Official leaderboard | |
| 468 | princeton-nlp Mistral-7B-Instruct-CPO 7.2B | 40.3% | chat models, bfloat16 | Official leaderboard | |
| 469 | huihui-ai Qwen2.5-7B-Instruct-abliterated 7.6B | 40.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 470 | inceptionai jais-family-30b-8k-chat | 40.3% | , ? | Official leaderboard | |
| 471 | FreedomIntelligence AceGPT-v2-70B 70.6B | 40.3% | pretrained, float16 | Official leaderboard | |
| 472 | sambanovasystems SambaLingo-Arabic-Chat 7B | 40.3% | chat models, bfloat16 | Official leaderboard | |
| 473 | 01-ai/Yi-1.5-9B-32K 8.8B | 40.3% | pretrained, bfloat16 | Official leaderboard | |
| 474 | google/gemma-7b-it 8.5B | 40.3% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 475 | grimjim Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge 8B | 40.3% | base merges and moerges, bfloat16 | Official leaderboard | |
| 476 | kaist-ai mistral-orpo-capybara-7k 7.2B | 40.3% | chat models, bfloat16 | Official leaderboard | |
| 477 | nbeerbower DeepSeek-R1-Qwen-lorablated-32B 32.8B | 40.3% | base merges and moerges, bfloat16 | Official leaderboard | |
| 478 | | 40.2% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 479 | grimjim Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge 8B | 40.2% | base merges and moerges, bfloat16 | Official leaderboard | |
| 480 | | 40.2% | chat models, bfloat16 | Apr 2024 | Official leaderboard |
| 481 | BAAI Infinity-Instruct-7M-Gen-Llama3_1-70B 70.6B | 40.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 482 | | 40.2% | pretrained, bfloat16 | Jul 2024 | Official leaderboard |
| 483 | GritLM GritLM-8x7B-KTO 46.7B | 40.2% | chat models, bfloat16 | Official leaderboard | |
| 484 | ibivibiv llama-3-nectar-dpo-8B | 40.2% | , ? | Official leaderboard | |
| 485 | Magpie-Align MagpieLM-8B-SFT-v0.1 8B | 40.2% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 486 | qnguyen3 Master-Yi-9B 8.8B | 40.2% | chat models, bfloat16 | Official leaderboard | |
| 487 | Daemontatox MawaredT1 | 40.2% | , bfloat16 | Official leaderboard | |
| 488 | EpistemeAI2 Fireball-Llama-3.1-8B-Philos-Relection | 40.1% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 489 | tiiuae/Falcon3-10B-Base 10.3B | 40.1% | pretrained, bfloat16 | Official leaderboard | |
| 490 | nbeerbower mistral-nemo-wissenschaft-12B 12.3B | 40.1% | chat models, bfloat16 | Official leaderboard | |
| 491 | | 40.1% | chat models, bfloat16 | Apr 2024 | Official leaderboard |
| 492 | Kukedlc NeuralLLaMa-3-8b-ORPO-v0.3 8B | 40.1% | chat models, float16 | Official leaderboard | |
| 493 | | 40.1% | pretrained, bfloat16 | Mar 2023 | Official leaderboard |
| 494 | core42 jais-30b-chat-v3 | 40.1% | , ? | Official leaderboard | |
| 495 | failspy Codestral-22B-v0.1-abliterated-v3 22.3B | 40.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 496 | NLPark AnFeng_v3.1-Avocet 34.4B | 40.1% | chat models, float16 | Official leaderboard | |
| 497 | Ali-C137 F1H10M-0000 6.9B | 40.1% | pretrained, bfloat16 | Official leaderboard | |
| 498 | | 40.1% | pretrained, bfloat16 | Apr 2023 | Official leaderboard |
| 499 | Kukedlc NeuralLLaMa-3-8b-DT-v0.1 8B | 40.1% | base merges and moerges, float16 | Official leaderboard | |
| 500 | migtissera Llama-3-70B-Synthia-v3.5 70.6B | 40.1% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 501 | princeton-nlp Mistral-7B-Base-SFT-KTO 7.2B | 40.1% | chat models, bfloat16 | Official leaderboard | |
| 502 | OpenBuddy openbuddy-qwen2.5llamaify-7b-v23.1-200k 7.6B | 40.1% | chat models, bfloat16 | Official leaderboard | |
| 503 | migtissera Tess-v2.5-Qwen2-72B 72.7B | 40.1% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 504 | 01-ai/Yi-1.5-9B 8.8B | 40.1% | pretrained, bfloat16 | Official leaderboard | |
| 505 | princeton-nlp Llama-3-Instruct-8B-CPO 8B | 40.1% | chat models, bfloat16 | Official leaderboard | |
| 506 | terrycraddock Reflection-Llama-3.1-8B 8B | 40.1% | chat models, float16 | Official leaderboard | |
| 507 | yellowtown 7B-v0.2 7.6B | 40.1% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 508 | maywell Synatra-7B-v0.3-RP | 40% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 509 | SakanaAI DiscoPOP-zephyr-7b-gemma 8.5B | 40% | chat models, bfloat16 | Official leaderboard | |
| 510 | kaist-ai janus-rm-7b 7.1B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 511 | GritLM GritLM-8x7B 46.7B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 512 | riotu-lab ArabianGPT-08B-V2 | 40% | , ? | Official leaderboard | |
| 513 | MarinaraSpaghetti NemoReRemix-12B 12.3B | 40% | base merges and moerges, bfloat16 | Official leaderboard | |
| 514 | huihui-ai DeepSeek-R1-Distill-Qwen-32B-abliterated 32.8B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 515 | Ali-C137 L2H10M-0000 6.7B | 40% | pretrained, bfloat16 | Official leaderboard | |
| 516 | kaist-ai janus-dpo-7b 7.2B | 40% | chat models, bfloat16 | Official leaderboard | |
| 517 | Magpie-Align Llama-3.1-8B-Magpie-Align-SFT-v0.1 8B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 518 | meta-llama/Llama-2-7b-hf 6.7B | 40% | pretrained, float16 | Official leaderboard | |
| 519 | princeton-nlp Mistral-7B-Base-SFT-RRHF 7.2B | 40% | chat models, bfloat16 | Official leaderboard | |
| 520 | Danielbrdz Barcenas-Llama3-8b-ORPO 8B | 40% | chat models, float16 | Official leaderboard | |
| 521 | kaist-ai janus-7b 7.2B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 522 | NTQAI Nxcode-CQ-7B-orpo 7.3B | 40% | chat models, bfloat16 | Official leaderboard | |
| 523 | princeton-nlp Llama-3-8B-ProLong-64k-Instruct | 40% | , ? | Official leaderboard | |
| 524 | SenseLLM ReflectionCoder-CL-34B 33.7B | 40% | chat models, bfloat16 | Official leaderboard | |
| 525 | google/gemma-2b-it 2.5B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 526 | MaziyarPanahi Mistral-7B-Instruct-v0.3 7.3B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 527 | migtissera Tess-2.0-Llama-3-70B 70.6B | 40% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 528 | mistralai/Mistral-7B-Instruct-v0.3 7.3B | 40% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 529 | utter-project EuroLLM-9B-Instruct 9.2B | 40% | chat models, bfloat16 | Official leaderboard | |
| 530 | abacusai bigstral-12b-32k 12.5B | 40% | base merges and moerges, float16 | Official leaderboard | |
| 531 | FreedomIntelligence AceGPT-v1.5-13B | 39.9% | , ? | Official leaderboard | |
| 532 | princeton-nlp Mistral-7B-Instruct-ORPO 7.2B | 39.9% | chat models, bfloat16 | Official leaderboard | |
| 533 | princeton-nlp Mistral-7B-Instruct-SLiC-HF 7.2B | 39.9% | chat models, bfloat16 | Official leaderboard | |
| 534 | inceptionai jais-adapted-13b | 39.9% | , ? | Official leaderboard | |
| 535 | princeton-nlp Llama-3-8B-ProLong-512k-Instruct | 39.9% | , ? | Official leaderboard | |
| 536 | meta-llama/Meta-Llama-3-8B-Instruct 8B | 39.9% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 537 | Triangle104 DeepSky-T100 32.8B | 39.9% | base merges and moerges, float16 | Official leaderboard | |
| 538 | | 39.9% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 539 | ghost-x ghost-8b-beta-1608 8B | 39.9% | chat models, bfloat16 | Official leaderboard | |
| 540 | mlabonne ChimeraLlama-3-8B-v3 8B | 39.9% | base merges and moerges, float16 | Official leaderboard | |
| 541 | UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter3 8B | 39.9% | chat models, bfloat16 | Official leaderboard | |
| 542 | 2A2I-R L1000MT 8B | 39.9% | pretrained, bfloat16 | Official leaderboard | |
| 543 | 2A2I-R L100MT 8B | 39.9% | pretrained, bfloat16 | Official leaderboard | |
| 544 | 2A2I-R L200MT 8B | 39.9% | pretrained, bfloat16 | Official leaderboard | |
| 545 | 2A2I-R L500MT 8B | 39.9% | pretrained, bfloat16 | Official leaderboard | |
| 546 | SicariusSicariiStuff Qwen2.5-14B_Uncencored | 39.9% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 547 | UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter1 8B | 39.9% | chat models, bfloat16 | Official leaderboard | |
| 548 | dicta-il dictalm2.0-instruct 7.3B | 39.9% | chat models, bfloat16 | Official leaderboard | |
| 549 | UCLA-AGI Llama-3-Instruct-8B-SPPO-Iter2 | 39.9% | chat models, bfloat16 | Official leaderboard | |
| 550 | HeshamHaroon llama-3-instruct-slerp-arabic | 39.8% | , bfloat16 | Official leaderboard | |
| 551 | anthracite-org magnum-v2.5-12b-kto 12.3B | 39.8% | chat models, float16 | Official leaderboard | |
| 552 | bigscience bloom-7b1 7.1B | 39.8% | pretrained, float16 | Official leaderboard | |
| 553 | lightblue suzume-llama-3-8B-multilingual 8B | 39.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 554 | lightblue suzume-llama-3-8B-multilingual-orpo-borda-top25 8B | 39.8% | chat models, bfloat16 | Official leaderboard | |
| 555 | OpenBuddy openbuddy-llama3-70b-v21.2-32k 70.6B | 39.8% | chat models, bfloat16 | Official leaderboard | |
| 556 | paloalma ECE-TW3-JRGL-V3 72.3B | 39.8% | base merges and moerges, bfloat16 | Official leaderboard | |
| 557 | princeton-nlp Llama-3-Instruct-8B-IPO 8B | 39.8% | chat models, bfloat16 | Official leaderboard | |
| 558 | vicgalle Configurable-Llama-3-8B-v0.3 8B | 39.8% | chat models, float16 | Official leaderboard | |
| 559 | failspy Meta-Llama-3-8B-Instruct-abliterated-v3 8B | 39.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 560 | FreedomIntelligence AceGPT-v2-32B-Chat 32.5B | 39.8% | chat models, float16 | Official leaderboard | |
| 561 | google/recurrentgemma-2b-it 2.7B | 39.8% | chat models, bfloat16 | Official leaderboard | |
| 562 | CohereForAI/c4ai-command-r-plus-08-2024 103.8B | 39.8% | chat models, float16 | Official leaderboard | |
| 563 | Sakalti Saka-24B 23.6B | 39.8% | base merges and moerges, float16 | Official leaderboard | |
| 564 | | 39.8% | pretrained, bfloat16 | Jul 2024 | Official leaderboard |
| 565 | | 39.8% | fine-tuned on domain-specific datasets, bfloat16 | Jan 2025 | Official leaderboard |
| 566 | FreedomIntelligence AceGPT-v1.5-13B-Chat | 39.8% | , ? | Official leaderboard | |
| 567 | gaverfraxz Meta-Llama-3.1-8B-Instruct-HalfAbliterated-TIES 8B | 39.8% | base merges and moerges, float16 | Official leaderboard | |
| 568 | princeton-nlp Llama-3-Instruct-8B-RRHF 8B | 39.8% | chat models, bfloat16 | Official leaderboard | |
| 569 | princeton-nlp Llama-3-Instruct-8B-SLiC-HF 8B | 39.8% | chat models, bfloat16 | Official leaderboard | |
| 570 | v000000 SwallowMaid-8B-L3-SPPO-abliterated | 39.8% | , ? | Official leaderboard | |
| 571 | cognitivecomputations dolphin-2.7-mixtral-8x7b | 39.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 572 | speakleash Bielik-11B-v2.3-Instruct 11.2B | 39.8% | base merges and moerges, float16 | Official leaderboard | |
| 573 | aws-prototyping MegaBeam-Mistral-7B-512k 7.2B | 39.8% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 574 | ibivibiv llama3-8b-instruct-summary-combined | 39.8% | , ? | Official leaderboard | |
| 575 | Delta-Vector Odin-9B 9.2B | 39.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 576 | dfurman Llama-3-70B-Orpo-v0.1 70.6B | 39.7% | chat models, float16 | Official leaderboard | |
| 577 | recoilme recoilme-gemma-2-9B-v0.3 10.2B | 39.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 578 | BAAI Infinity-Instruct-7M-Gen-Llama3_1-8B 8B | 39.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 579 | migtissera Tess-2.0-Llama-3-70B-v0.2 70.6B | 39.7% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 580 | Nohobby Q2.5-Qwetiapin-32B 32.8B | 39.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 581 | | 39.7% | pretrained, bfloat16 | Apr 2024 | Official leaderboard |
| 582 | abacusai bigyi-15b 15.1B | 39.7% | base merges and moerges, float16 | Official leaderboard | |
| 583 | ai21labs AI21-Jamba-1.5-Mini 51.6B | 39.7% | pretrained, bfloat16 | Official leaderboard | |
| 584 | CohereForAI/c4ai-command-r-plus 103.8B | 39.7% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 585 | kaist-ai janus-orpo-7b 7.2B | 39.7% | chat models, bfloat16 | Official leaderboard | |
| 586 | tokyotech-llm Llama-3-Swallow-8B-Instruct-v0.1 8B | 39.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 587 | GritLM GritLM-7B 7.2B | 39.7% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 588 | rombodawg rombos_Replete-Coder-Instruct-8b-Merged 8B | 39.7% | base merges and moerges, bfloat16 | Official leaderboard | |
| 589 | | 39.7% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 590 | core42 jais-30b-v1 | 39.7% | , ? | Official leaderboard | |
| 591 | core42 jais-30b-v3 | 39.7% | , ? | Official leaderboard | |
| 592 | inceptionai jais-family-30b-8k | 39.7% | , ? | Official leaderboard | |
| 593 | princeton-nlp Llama-3-Instruct-8B-ORPO 8B | 39.7% | chat models, bfloat16 | Official leaderboard | |
| 594 | sambanovasystems SambaLingo-Arabic-Base-70B | 39.7% | , ? | Official leaderboard | |
| 595 | utter-project EuroLLM-9B 9.2B | 39.7% | pretrained, bfloat16 | Official leaderboard | |
| 596 | | 39.7% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 597 | SeaLLMs SeaLLMs-v3-7B-Chat 7.6B | 39.7% | chat models, bfloat16 | Official leaderboard | |
| 598 | anthracite-org magnum-v4-9b 9.2B | 39.7% | chat models, bfloat16 | Official leaderboard | |
| 599 | Qwen/Qwen2.5-7B-Instruct 7.6B | 39.7% | chat models, bfloat16 | Official leaderboard | |
| 600 | abacusai Llama-3-Smaug-8B 8B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 601 | inceptionai jais-family-1p3b-chat | 39.6% | , ? | Official leaderboard | |
| 602 | natong19 Mistral-Nemo-Instruct-2407-abliterated 12.3B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 603 | OpenBuddy openbuddy-yi1.5-34b-v21.6-32k-fp16 34.4B | 39.6% | chat models, float16 | Official leaderboard | |
| 604 | Replete-AI Replete-LLM-V2.5-Qwen-7b 7.6B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 605 | Ali-C137 M03H10M-0000 7.3B | 39.6% | pretrained, bfloat16 | Official leaderboard | |
| 606 | MaziyarPanahi Mistral-7B-v0.3 7.3B | 39.6% | pretrained, bfloat16 | Official leaderboard | |
| 607 | nyunai nyun-c2-llama3-56B 55.6B | 39.6% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 608 | | 39.6% | pretrained, bfloat16 | Sep 2023 | Official leaderboard |
| 609 | | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Jan 2025 | Official leaderboard |
| 610 | inceptionai jais-adapted-7b | 39.6% | , ? | Official leaderboard | |
| 611 | Kukedlc NeuralLLaMa-3-8b-ORPO-v0.4 8B | 39.6% | chat models, float16 | Official leaderboard | |
| 612 | sambanovasystems SambaLingo-Arabic-Base | 39.6% | , ? | Official leaderboard | |
| 613 | turboderp Cat-Llama-3-70B-instruct 70.6B | 39.6% | chat models, float16 | Official leaderboard | |
| 614 | dfurman Llama-3-8B-Orpo-v0.1 8B | 39.6% | chat models, float16 | Official leaderboard | |
| 615 | inceptionai jais-family-30b-16k | 39.6% | , ? | Official leaderboard | |
| 616 | MaziyarPanahi calme-2.3-qwen2-72b 72.7B | 39.6% | chat models, bfloat16 | Official leaderboard | |
| 617 | MaziyarPanahi calme-2.3-qwen2-7b 7.6B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 618 | Qwen/Qwen2.5-3B-Instruct 3.1B | 39.6% | chat models, bfloat16 | Official leaderboard | |
| 619 | speakleash Bielik-11B-v2 11.2B | 39.6% | pretrained, bfloat16 | Official leaderboard | |
| 620 | vicgalle Configurable-Hermes-3-Llama-3.1-8B 8B | 39.6% | chat models, float16 | Official leaderboard | |
| 621 | maywell Qwen2-7B-Multilingual-RP 7.6B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 622 | MaziyarPanahi calme-2.2-qwen2-7b 7.6B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 623 | MaziyarPanahi calme-2.4-qwen2-7b 7.6B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 624 | prithivMLmods Qwen2.5-32B-DeepSeek-R1-Instruct 32.8B | 39.6% | base merges and moerges, bfloat16 | Official leaderboard | |
| 625 | RDson CoderO1-DeepSeekR1-Coder-32B-Preview 32.8B | 39.6% | base merges and moerges, bfloat16 | Official leaderboard | |
| 626 | riotu-lab ArabianGPT-1.5B | 39.6% | , ? | Official leaderboard | |
| 627 | GritLM GritLM-7B-KTO 7.2B | 39.6% | chat models, bfloat16 | Official leaderboard | |
| 628 | Sakalti Saka-7.6B 7.6B | 39.6% | base merges and moerges, float16 | Official leaderboard | |
| 629 | sambanovasystems SambaLingo-Arabic-Chat-70B | 39.6% | , ? | Official leaderboard | |
| 630 | SicariusSicariiStuff Qwen2.5-14B_Uncensored_Instruct 14.8B | 39.6% | chat models, float16 | Official leaderboard | |
| 631 | arcee-ai Arcee-Spark 7.6B | 39.6% | chat models, bfloat16 | Official leaderboard | |
| 632 | mlabonne FineLlama-3.1-8B 8B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 633 | mlabonne Meta-Llama-3.1-8B-Instruct-abliterated 8B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 634 | NaniDAO deepseek-r1-qwen-2.5-32B-ablated 32.8B | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 635 | NousResearch Hermes-3-Llama-3.1-8B 8B | 39.6% | chat models, bfloat16 | Official leaderboard | |
| 636 | | 39.6% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 637 | dicta-il dictalm2.0 7.3B | 39.6% | pretrained, bfloat16 | Official leaderboard | |
| 638 | MohamedRashad Arabic-Orpo-Llama-3-8B-Instruct 8B | 39.6% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 639 | | 39.6% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 640 | Ali-C137 PG7BB 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 641 | Ali-C137 Q2AW1M-0000 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 642 | Ali-C137 Q2AW1M-0010 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 643 | Ali-C137 Q2AW1M-0100 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 644 | Ali-C137 Q2AW1M-1000 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 645 | Ali-C137 Q2AW1M-1010 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 646 | Ali-C137 Q2AW1M-1100 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 647 | Ali-C137 Q2H10M-0000 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 648 | informatiker Qwen2-7B-Instruct-abliterated 7.6B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 649 | MaziyarPanahi calme-2.5-qwen2-7b 7.6B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 650 | natong19 Qwen2-7B-Instruct-abliterated 7.6B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 651 | prithivMLmods Qwen2.5-14B-DeepSeek-R1-1M 14.8B | 39.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 652 | | 39.5% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 653 | | 39.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 654 | | 39.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 655 | inceptionai jais-family-590m-chat | 39.5% | , ? | Official leaderboard | |
| 656 | VAGOsolutions SauerkrautLM-Nemo-12b-Instruct 12.3B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 657 | cognitivecomputations dolphin-2.9.4-llama3.1-8b 8B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 658 | FreedomIntelligence AceGPT-v2-70B-Chat 70.6B | 39.5% | chat models, float16 | Official leaderboard | |
| 659 | nicoboss DeepSeek-R1-Distill-Qwen-32B-Uncensored 32.8B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 660 | tiiuae/Falcon3-3B-Base 3.2B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 661 | | 39.5% | pretrained, bfloat16 | Jun 2024 | Official leaderboard |
| 662 | AXCXEPT EZO-Qwen2.5-32B-Instruct 32.8B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 663 | inceptionai jais-family-13b | 39.5% | , ? | Official leaderboard | |
| 664 | NousResearch Nous-Hermes-2-Mixtral-8x7B-DPO 46.7B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 665 | Qwen/Qwen2-MoE-57B-A14B | 39.5% | , bfloat16 | Official leaderboard | |
| 666 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 667 | abacusai Liberated-Qwen1.5-14B | 39.5% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 668 | AIDC-AI Marco-LLM-AR 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 669 | Ali-C137 Q2AW1M-0001 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 670 | Ali-C137 Q2AW1M-0111 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 671 | Ali-C137 Q2AW1M-1001 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 672 | Ali-C137 Q2AW1M-1111 7.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 673 | asas-ai AceGPT-v2-32B 32.5B | 39.5% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 674 | BAAI Infinity-Instruct-3M-0625-Qwen2-7B 7.6B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 675 | cognitivecomputations dolphin-2.9.2-qwen2-7b 7.6B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 676 | core42 jais-13b | 39.5% | , ? | Official leaderboard | |
| 677 | Cran-May T.E-8.1 7.6B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 678 | FreedomIntelligence AceGPT-v2-32B | 39.5% | , float16 | Official leaderboard | |
| 679 | HeshamHaroon Testv1 7.6B | 39.5% | chat models, float16 | Official leaderboard | |
| 680 | hotmailuser Deeepseek-QwenSlerp4-32B 32.8B | 39.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 681 | inceptionai jais-family-1p3b | 39.5% | , ? | Official leaderboard | |
| 682 | inceptionai jais-family-2p7b | 39.5% | , ? | Official leaderboard | |
| 683 | inceptionai jais-family-590m | 39.5% | , ? | Official leaderboard | |
| 684 | inceptionai jais-family-6p7b | 39.5% | , ? | Official leaderboard | |
| 685 | macadeliccc Samantha-Qwen-2-7B 7.6B | 39.5% | fine-tuned on domain-specific datasets, float16 | Official leaderboard | |
| 686 | MaziyarPanahi calme-2.1-qwen2-7b 7.6B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 687 | MaziyarPanahi calme-2.6-qwen2-7b 7.6B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 688 | MaziyarPanahi calme-2.7-qwen2-7b 7.6B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 689 | MBZUAI MobiLlama-1B | 39.5% | , ? | Official leaderboard | |
| 690 | nitky RoguePlanet-DeepSeek-R1-Qwen-32B 32.8B | 39.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 691 | oddadmix Arabic-Qwen2.5-3B 3.1B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 692 | oddadmix Arabic-Qwen2.5-3B-v2 3.1B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 693 | oddadmix Arabic-Qwen2.5-3B-v2.1 3.1B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 694 | OpenBuddy openbuddy-qwen1.5-32b-v21.1-32k 32.5B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 695 | OpenBuddy openbuddy-qwen1.5-32b-v21.2-32k 32.5B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 696 | Orion-zhen Qwen2.5-7B-Instruct-Uncensored 7.6B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 697 | paloalma ECE-TW3-JRGL-V2 72.3B | 39.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 698 | Qwen/Qwen1.5-0.5B 0.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 699 | Qwen/Qwen1.5-0.5B-Chat 0.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 700 | Qwen/Qwen1.5-32B-Chat 32.5B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 701 | Qwen/Qwen1.5-4B 4B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 702 | Qwen/Qwen1.5-MoE-A2.7B 14.3B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 703 | Qwen/Qwen1.5-MoE-A2.7B-Chat 14.3B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 704 | Qwen/Qwen2-MoE-57B-A14B-Instruct | 39.5% | , bfloat16 | Official leaderboard | |
| 705 | Qwen/Qwen2.5-1.5B-Instruct 1.5B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 706 | Qwen/Qwen2.5-Math-7B-Instruct 7.6B | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 707 | Sakalti Saka-1.5B 1.8B | 39.5% | base merges and moerges, float16 | Official leaderboard | |
| 708 | TeetouchQQ model_mergev2 32.8B | 39.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 709 | VAGOsolutions SauerkrautLM-Qwen-32b 32.5B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 710 | vilm Quyen-Pro-Max-v0.1 | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 711 | Weyaxi Einstein-v7-Qwen2-7B 7.6B | 39.5% | chat models, bfloat16 | Official leaderboard | |
| 712 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 713 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 714 | | 39.5% | pretrained, bfloat16 | Apr 2024 | Official leaderboard |
| 715 | | 39.5% | pretrained, bfloat16 | Jun 2024 | Official leaderboard |
| 716 | | 39.5% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 717 | | 39.5% | pretrained, bfloat16 | Jun 2024 | Official leaderboard |
| 718 | | 39.5% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 719 | | 39.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 720 | Qwen2.5-Coder-14B-Instruct | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Nov 2024 | Official leaderboard |
| 721 | ai21labs Jamba-v0.1 51.6B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 722 | google/recurrentgemma-2b | 39.5% | , ? | Official leaderboard | |
| 723 | Slim205 Barka-2b-it | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 724 | Qwen/Qwen1.5-110B-Chat 111.2B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 725 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 726 | Ali-C137 Q15H10M-0000 7.7B | 39.5% | pretrained, bfloat16 | Official leaderboard | |
| 727 | paloalma ECE-TW3-JRGL-V4 72.3B | 39.5% | base merges and moerges, bfloat16 | Official leaderboard | |
| 728 | Ali-C137 L3H10M-0000 8B | 39.4% | pretrained, bfloat16 | Official leaderboard | |
| 729 | | 39.4% | pretrained, bfloat16 | Apr 2024 | Official leaderboard |
| 730 | princeton-nlp Llama-3-8B-ProLong-64k-Base | 39.4% | , ? | Official leaderboard | |
| 731 | rombodawg rombos_Replete-Coder-Llama3-8B 8B | 39.4% | fine-tuned on domain-specific datasets, bfloat16 | Official leaderboard | |
| 732 | unsloth llama-3-8b-bnb-4bit | 39.2% | , GPTQ | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 73.9% | fine-tuned on domain-specific datasets, bfloat16 | Sep 2024 | Official leaderboard |
| 2 | | 63.9% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 3 | | 62.1% | chat models, bfloat16 | Sep 2024 | Official leaderboard |
| 4 | | 61.3% | fine-tuned on domain-specific datasets, bfloat16 | Jan 2025 | Official leaderboard |
| 5 | | 59.5% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 6 | | 59% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 7 | | 55.2% | chat models, bfloat16 | Apr 2024 | Official leaderboard |
| 8 | | 52.5% | chat models, bfloat16 | May 2024 | Official leaderboard |
| 9 | | 49.6% | pretrained, bfloat16 | Sep 2023 | Official leaderboard |
| 10 | | 47.8% | chat models, bfloat16 | May 2024 | Official leaderboard |
| 11 | | 47.6% | , ? | Jun 2024 | Official leaderboard |
| 12 | | 47.6% | fine-tuned on domain-specific datasets, float16 | Mar 2024 | Official leaderboard |
| 13 | | 47.6% | chat models, bfloat16 | Jan 2025 | Official leaderboard |
| 14 | | 46.5% | pretrained, bfloat16 | May 2024 | Official leaderboard |
| 15 | | 45.1% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 16 | | 44% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 17 | | 43.2% | chat models, bfloat16 | Dec 2023 | Official leaderboard |
| 18 | | 42.6% | chat models, float16 | Oct 2024 | Official leaderboard |
| 19 | | 41.9% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 20 | | 41.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 21 | | 41.5% | chat models, bfloat16 | Dec 2024 | Official leaderboard |
| 22 | | 41.4% | , ? | Jun 2024 | Official leaderboard |
| 23 | | 40.6% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 24 | Qwen2.5-Coder-14B | 40.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 25 | c4ai-command-r-08-2024 | 40.5% | chat models, float16 | Aug 2024 | Official leaderboard |
| 26 | | 40.2% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 27 | | 40.2% | chat models, bfloat16 | Apr 2024 | Official leaderboard |
| 28 | | 40.2% | pretrained, bfloat16 | Jul 2024 | Official leaderboard |
| 29 | | 40.1% | chat models, bfloat16 | Apr 2024 | Official leaderboard |
| 30 | | 40.1% | pretrained, bfloat16 | Mar 2023 | Official leaderboard |
| 31 | | 40.1% | pretrained, bfloat16 | Apr 2023 | Official leaderboard |
| 32 | | 39.9% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 33 | | 39.8% | pretrained, bfloat16 | Jul 2024 | Official leaderboard |
| 34 | | 39.8% | fine-tuned on domain-specific datasets, bfloat16 | Jan 2025 | Official leaderboard |
| 35 | | 39.7% | pretrained, bfloat16 | Apr 2024 | Official leaderboard |
| 36 | | 39.7% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 37 | | 39.7% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 38 | | 39.6% | pretrained, bfloat16 | Sep 2023 | Official leaderboard |
| 39 | | 39.6% | fine-tuned on domain-specific datasets, bfloat16 | Jan 2025 | Official leaderboard |
| 40 | | 39.6% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 41 | | 39.6% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 42 | | 39.5% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 43 | | 39.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 44 | | 39.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 45 | | 39.5% | pretrained, bfloat16 | Jun 2024 | Official leaderboard |
| 46 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 47 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 48 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 49 | | 39.5% | pretrained, bfloat16 | Apr 2024 | Official leaderboard |
| 50 | | 39.5% | pretrained, bfloat16 | Jun 2024 | Official leaderboard |
| 51 | | 39.5% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 52 | | 39.5% | pretrained, bfloat16 | Jun 2024 | Official leaderboard |
| 53 | | 39.5% | chat models, bfloat16 | Jun 2024 | Official leaderboard |
| 54 | | 39.5% | pretrained, bfloat16 | Sep 2024 | Official leaderboard |
| 55 | Qwen2.5-Coder-14B-Instruct | 39.5% | fine-tuned on domain-specific datasets, bfloat16 | Nov 2024 | Official leaderboard |
| 56 | | 39.5% | pretrained, bfloat16 | Feb 2024 | Official leaderboard |
| 57 | | 39.4% | pretrained, bfloat16 | Apr 2024 | Official leaderboard |
5 models have held number one on Open Arabic LLM Leaderboard v1’s leaderboard since its release in September 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Open Arabic LLM Leaderboard v1’s leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Open Arabic LLM Leaderboard v1’s leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 22 months ago, in January 2025, for Qwen2.5-14B-Instruct-1M. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (732 entries).
- Pass Models scored 57 models we track, plus 675 other entries on its leaderboard.
- Warning Newest score The newest came 22 months ago, in January 2025, for Qwen2.5-14B-Instruct-1M.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen2.5-72B (#166).
- Pass Headroom The best is 73.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on Open Arabic LLM Leaderboard v1: 62 rows for models we track and 675 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.