Open Chinese LLM Leaderboard
Models answer Chinese language tasks. The leaderboard compares model results across its evaluation suite.
The open leaderboard Space has 128 likes on Hugging Face.
- Released
- May 2024
- Kind
- Knowledge in many languages
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Chinese
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Qwen2-72B #180 on the capability index
- Last model added
- June 2024
- Scores refreshed
- November 21st, 2026
Qwen2-72B leads with 75.7 among models released by June 2024 Qwen2-72B leads with 75.7 among models released by June 2024
Best score per entry from the benchmark's own leaderboard, read on November 21st, 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. This view shows only models we track, each at its best.
The newest model with a score here came out in June 2024, 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
- 75.7
Qwen2-72B
- 74.6 freewheelin/free-evo-qwen72b-v0.8-re 📑 has been flagged! See discussion #510
- 74.3 davidkim205/Rhea-72b-v0.5 📑
- 73.3 paloalma/TW3-JRGL-v2 📑
- 73.2 abacusai/Smaug-72B-v0.1 📑
- 72.1 MTSAIR/MultiVerse_70B 📑
- 72.0 paloalma/Le_Triomphant-ECE-TW3 📑
- 71.7 saltlux/luxia-21.4b-alignment-v1.0 📑
- 71.2 paloalma/ECE-TW3-JRGL-V5 📑
- 70.9 CombinHorizon/YiSM-blossom5.1-34B-SLERP 📑
- 70.8 Weyaxi/Bagel-Hermes-34B-Slerp 📑
- 70.7 fblgit/UNA-SimpleSmaug-34b-v1beta 📑
- 70.6 abacusai/Smaug-34B-v0.1 📑
- 70.6 cloudyu/Yi-34Bx2-MoE-60B-DPO 📑
- 70.5
Qwen1.5-72B
- 70.4 cloudyu/Yi-34Bx2-MoE-60B 📑
- 70.4 ConvexAI/Luminex-34B-v0.2 📑
- 70.3 ConvexAI/Luminex-34B-v0.1 📑
- 69.6 cloudyu/Yi-34Bx2-MOE-200K 📑
- 69.6 OpenBuddy/openbuddy-yi1.5-34b-v21.3-32k 📑
- 69.4 saltlux/luxia-21.4b-alignment-v1.2 📑
- 69.4 cloudyu/Mixtral_34Bx2_MoE_60B 📑
- 69.4 migtissera/Llama-3-70B-Synthia-v3.5 📑
- 69.4 bosonai/Higgs-Llama-3-70B 📑
- 69.4 jondurbin/bagel-dpo-34b-v0.2 📑
- 69.3 OpenBuddy/openbuddy-deepseek-67b-v18.1-4k 📑
- 69.1 abacusai/Smaug-Llama-3-70B-Instruct 📑
- 68.9 01-ai/Yi-1.5-34B-Chat 📑
- 68.9 OpenBuddy/openbuddy-llama3-70b-v21.2-32k 📑
- 68.7 Qwen/Qwen2-57B-A14B-Instruct 📑
- 68.7 Azure99/blossom-v5.1-34b 📑
- 68.4 altomek/YiSM-34B-0rn 📑
- 68.4 gbueno86/Meta-LLama-3-Cat-Smaug-LLama-70b 📑
- 67.9 migtissera/Tess-2.0-Llama-3-70B 📑
- 67.9 tenyx/Llama3-TenyxChat-70B 📑
- 67.8 cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 📑
- 67.8 wenbopan/Faro-Yi-34B-DPO 📑
- 67.6 OpenBuddy/openbuddy-zero-56b-v21.2-32k 📑
- 67.6 chujiezheng/Llama3-70B-Chinese-Chat-ExPO 📑
- 67.5 chujiezheng/Smaug-34B-v0.1-ExPO 📑
- 67.5 MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2 📑
- 67.5 failspy/Smaug-Llama-3-70B-Instruct-abliterated-v3 📑
- 67.5 cognitivecomputations/dolphin-2.9.1-yi-1.5-34b 📑
- 67.3 failspy/llama-3-70B-Instruct-abliterated 📑
- 67.3 Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 📑
- 67.1 brucethemoose/Yi-34B-200K-DARE-merge-v7 📑
- 67.0 abacusai/Smaug-Llama-3-70B-Instruct-32K 📑
- 67.0 chujiezheng/Smaug-Llama-3-70B-Instruct-ExPO 📑
- 66.9 01-ai/Yi-1.5-34B-Chat-16K 📑
- 66.8 01-ai/Yi-1.5-34B-32K 📑
- 66.7
Yi-1.5-34B
- 66.6
Qwen1.5-32B
- 66.6 gbueno86/Meta-LLama-3-Cat-A-LLama-70b 📑
- 66.5 Qwen/Qwen2-57B-A14B 📑
- 66.2 mmnga/Llama-3-70B-japanese-suzume-vector-v0.1 📑
- 66.1 cognitivecomputations/dolphin-2.9.1-llama-3-70b 📑
- 66.0
Qwen1.5-14B-Chat
- 65.7 Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO 📑
- 65.6 BAAI/Infinity-Instruct-3M-0625-Yi-1.5-9B 📑
- 65.4 VAGOsolutions/SauerkrautLM-Phi-3-medium 📑
- 65.3
Yi-34B
- 65.3 ValiantLabs/Llama3-70B-ShiningValiant2 📑
- 65.2 wenbopan/Faro-Yi-34B 📑
- 64.7 CausalLM/34b-beta 📑
- 64.6 OpenBuddy/openbuddy-yi1.5-34b-v21.6-32k-fp16 📑
- 64.4 wenbopan/Faro-Yi-9B-DPO 📑
- 64.4 deepseek-ai/deepseek-llm-67b-base 📑
- 64.3
Yi-1.5-9B-Chat
- 64.2 Duxiaoman-DI/XuanYuan-70B 📑
- 64.2
WizardLM-2 8x22B
- 64.0 vicgalle/Configurable-Yi-1.5-9B-Chat 📑
- 64.0 cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k 📑
- 63.9 internlm/internlm2-20b 📑
- 63.9 NousResearch/Nous-Hermes-2-Yi-34B 📑
- 63.7 NLPark/AnFeng_v3_Avocet 📑
- 63.5
Qwen2-7B
- 63.5 byroneverson/Yi-1.5-9B-Chat-16K-abliterated 📑
- 63.4 jondurbin/bagel-dpo-34b-v0.5 📑
- 63.3 paloalma/ECE-TW3-JRGL-V1 📑
- 63.2
MAmmoTH2-8x7B-Plus
- 63.0 OpenBuddy/openbuddy-yi1.5-9b-v21.1-32k 📑
- 62.9 byroneverson/Yi-1.5-9B-Chat-abliterated 📑
- 62.9 NLPark/Shi-Ci_v3-Robin 📑
- 62.9 cognitivecomputations/dolphin-2.9.1-yi-1.5-9b 📑
- 62.9 wenbopan/Faro-Yi-9B 📑
- 62.6 qnguyen3/Master-Yi-9B 📑
- 62.6 Qwen/Qwen1.5-32B-Chat 📑
- 62.5 01-ai/Yi-1.5-9B-Chat-16K 📑
- 62.4 cognitivecomputations/dolphin-2.9.2-mixtral-8x22b 📑
- 62.4 duoqi/Nanbeige2-16B-Chat 📑
- 61.9 01-ai/Yi-1.5-9B-32K 📑
- 61.8 01-ai/Yi-1.5-9B 📑
- 61.8
Qwen2-7B-Instruct
- 61.6
Qwen1.5-14B
- 61.3 chujiezheng/internlm2-chat-20b-ExPO 📑
- 61.2 migtissera/Tess-2.0-Llama-3-70B-v0.2 📑
- 60.9 failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5 📑
- 60.9 migtissera/Tess-M-v1.3 📑
- 60.8 ValiantLabs/Llama3-70B-Fireplace 📑
- 60.6 BAAI/Infinity-Instruct-7M-0729-Llama3_1-8B 📑
- 60.5 byroneverson/Mistral-Small-Instruct-2409-abliterated 📑
- 60.5 internlm/internlm2-chat-7b 📑
- 60.5 Duxiaoman-DI/XuanYuan-70B-Chat 📑
- 60.2 internlm/internlm2-chat-20b 📑
- 60.2 xiangxinai/Xiangxin-2XL-Chat-1048k-Chinese-Llama3-70B 📑
- 60.2 Nous-Hermes-2-Mixtral-8x7B-DPO
- 60.1 sophosympatheia/Midnight-Miqu-70B-v1.5 📑
- 60.1 GritLM/GritLM-8x7B-KTO 📑
- 59.8 BAAI/Infinity-Instruct-3M-0625-Llama3-8B 📑
- 59.8 internlm/internlm2-7b 📑
- 59.7 Langboat/Mengzi3-8B-Chat 📑
- 59.7 chujiezheng/LLaMA3-iterative-DPO-final-ExPO 📑
- 59.6 CofeAI/Tele-FLM 📑
- 59.6 internlm/internlm2-base-20b 📑
- 59.4 01-ai/Yi-34B-Chat 📑
- 59.3 cognitivecomputations/dolphin-2.9.2-Phi-3-Medium 📑
- 59.2 vicgalle/CarbonBeagle-11B-truthy 📑
- 59.1 abhishek/autotrain-llama3-70b-orpo-v1 📑
- 59.0 shenzhi-wang/Llama3-8B-Chinese-Chat 📑
- 58.9 NotAiLOL/Yi-1.5-dolphin-9B 📑
- 58.7 vicgalle/CarbonBeagle-11B 📑
- 58.7 DeepMount00/Llama-3-8b-Ita 📑
- 58.7 VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct 📑
- 58.6 MaziyarPanahi/Llama-3-8B-Instruct-v0.8 📑
- 58.6 Kukedlc/NeuralLLaMa-3-8b-DT-v0.1 📑
- 58.5 GritLM/GritLM-8x7B 📑
- 58.5 mlabonne/Daredevil-8B-abliterated 📑
- 58.5 jondurbin/airoboros-70b-3.3 📑
- 58.4 yaojialzc/Gigi-Llama3-8B-Chinese-zh 📑
- 58.4 BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B 📑
- 58.4 jondurbin/airoboros-dpo-70b-3.3 📑
- 58.4 turboderp/Cat-Llama-3-70B-instruct 📑
- 58.3 Yi-9B
- 58.3 MaziyarPanahi/Llama-3-8B-Instruct-v0.10 📑
- 58.3 cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated 📑
- 58.3 mlabonne/NeuralDaredevil-8B-abliterated 📑
- 58.1 haoranxu/Llama-3-Instruct-8B-SimPO 📑
- 58.1 01-ai/Yi-9B-200K 📑
- 58.0 grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge 📑
- 58.0 OpenBuddy/openbuddy-llama3-8b-v21.2-32k 📑
- 58.0 vicgalle/ConfigurableBeagle-11B 📑
- 58.0 Danielbrdz/Barcenas-Llama3-8b-ORPO 📑
- 58.0 MaziyarPanahi/Llama-3-8B-Instruct-v0.9 📑
- 57.9 UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 📑
- 57.9 01-ai/Yi-34B-200K 📑
- 57.9 Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 📑
- 57.8 UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2 📑
- 57.7 mixtao/MixTAO-7Bx2-MoE-v8.1 📑
- 57.7 shadowml/BeagSake-7B 📑
- 57.7 shadowml/Mixolar-4x7b 📑
- 57.6 jeonsworld/CarbonVillain-en-10.7B-v4 📑
- 57.6 kekmodel/StopCarbon-10.7B-v5 📑
- 57.6 hfl/chinese-mixtral-instruct 📑
- 57.5 haoranxu/Llama-3-Instruct-8B-CPO-SimPO 📑
- 57.5 NLPark/Test1_SLIDE 📑
- 57.4 hfl/llama-3-chinese-8b-instruct-v2 📑
- 57.4 invalid-coder/Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp 📑
- 57.3 zhengr/MixTAO-7Bx2-MoE-v8.1 📑
- 57.3 dzakwan/dzakwan-MoE-4x7b-Beta 📑
- 57.3 RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2 📑
- 57.3 hfl/llama-3-chinese-8b-instruct-v3 📑
- 57.2 Magpie-Align/Llama-3-8B-Magpie-Align-v0.3 📑
- 57.2 ghost-x/ghost-8b-beta-1608 📑
- 57.2
SOLAR-10.7B-Instruct-v1.0
- 57.2 chujiezheng/Llama3-8B-Chinese-Chat-ExPO 📑
- 57.2 uygarkurt/llama-3-merged-linear 📑
- 57.0 jondurbin/bagel-8b-v1.0 📑
- 57.0 jsfs11/MixtureofMerges-MoE-4x7b-v5 📑
- 57.0 mlabonne/ChimeraLlama-3-8B-v3 📑
- 57.0
Yi-6B-Chat
- 57.0 Kukedlc/NeuralSynthesis-7B-v0.3 📑
- 56.9 mlabonne/AlphaMonarch-7B 📑
- 56.9 mlabonne/ChimeraLlama-3-8B-v2 📑
- 56.9 Kquant03/CognitiveFusion2-4x7B-BF16 📑
- 56.8 meraGPT/mera-mix-4x7B 📑
- 56.8 ibivibiv/multimaster-7b-v6 📑
- 56.8 vicgalle/Configurable-Llama-3-8B-v0.3 📑
- 56.7 Kukedlc/NeuralSynthesis-7B-v0.1 📑
- 56.7 yunconglong/DARE_TIES_13B 📑
- 56.7 mlabonne/NeuralMonarch-7B 📑
- 56.7 yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 📑
- 56.7 yunconglong/MoE_13B_DPO 📑
- 56.7 Kukedlc/NeuralSynthesis-7b-v0.4-slerp 📑
- 56.7 cognitivecomputations/WestLake-7B-v2-laser 📑
- 56.7 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half 📑
- 56.6 MaziyarPanahi/Calme-4x7B-MoE-v0.1 📑
- 56.6 grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge 📑
- 56.6 allknowingroger/MultiverseEx26-7B-slerp 📑
- 56.6 vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B 📑
- 56.6 jsfs11/MixtureofMerges-MoE-4x7b-v4 📑
- 56.6 Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3 📑
- 56.6 automerger/YamshadowExperiment28-7B 📑
- 56.6
Qwen1.5-7B
- 56.6 NousResearch/Hermes-2-Theta-Llama-3-8B 📑 has been flagged! See discussion #510
- 56.5 MaziyarPanahi/Calme-4x7B-MoE-v0.2 📑
- 56.4
MAmmoTH2-8B-Plus
- 56.4 CultriX/NeuralMona_MoE-4x7B 📑
- 56.3 hfl/llama-3-chinese-8b-instruct 📑
- 56.3 winninghealth/WiNGPT2-Llama-3-8B-Chat 📑
- 56.3 ibivibiv/llama-3-nectar-dpo-8B 📑
- 56.3 mlabonne/Beyonder-4x7B-v3 📑
- 56.3 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25 📑
- 56.2 chujiezheng/internlm2-chat-7b-ExPO 📑
- 56.2 Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4 📑
- 56.1 failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 📑
- 56.0 01-ai/Yi-1.5-6B 📑
- 56.0 lightblue/suzume-llama-3-8B-multilingual 📑
- 56.0 Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5 📑
- 55.9 MaziyarPanahi/Topxtral-4x7B-v0.1 📑
- 55.9 chujiezheng/tulu-2-dpo-70b-ExPO 📑
- 55.8 abacusai/Smaug-Mixtral-v0.1 📑
- 55.8 princeton-nlp/Llama-3-8B-ProLong-512k-Instruct 📑
- 55.7 vaiv/GeM2-Llamion-14B-Base 📑
- 55.6 OpenBuddy/openbuddy-zero-14b-v22.3-32k 📑
- 55.6 openchat/openchat-3.6-8b-20240522 📑
- 55.5 eldogbbhed/Peagle-9b 📑
- 55.4 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75 📑
- 55.3 abacusai/Slerp-CM-mist-dpo 📑
- 55.2 migtissera/Llama-3-8B-Synthia-v3.5 📑
- 55.1 failspy/Codestral-22B-v0.1-abliterated-v3 📑
- 55.1 NousResearch/Meta-Llama-3-8B-Instruct 📑
- 55.0 duoqi/Nanbeige-16B-Base-Llama 📑
- 54.9 princeton-nlp/Llama-3-8B-ProLong-64k-Instruct 📑
- 54.8 Qwen/Qwen1.5-MoE-A2.7B 📑
- 54.8 NousResearch/Nous-Hermes-2-SOLAR-10.7B 📑
- 54.7 HIT-SCIR/Chinese-Mixtral-8x7B 📑
- 54.6 hfl/chinese-mixtral 📑
- 54.6 princeton-nlp/Llama-3-8B-ProLong-64k-Base 📑
- 54.6 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full 📑
- 54.5 rombodawg/rombos_Replete-Coder-Instruct-8b-Merged 📑
- 54.5 liminerity/M7-7b 📑
- 54.3 deepseek-ai/deepseek-llm-7b-chat 📑
- 54.1 princeton-nlp/Llama-3-8B-ProLong-512k-Base 📑
- 54.1 Weyaxi/Einstein-v6.1-Llama3-8B 📑
- 53.8 cognitivecomputations/openchat-3.5-0106-laser 📑
- 53.7 openchat/openchat-3.5-0106 📑
- 53.7 chujiezheng/Starling-LM-7B-beta-ExPO 📑
- 53.7 freewheelin/free-solar-evo-v0.13 📑
- 53.7 abacusai/Llama-3-Smaug-8B 📑
- 53.6 cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2 📑
- 53.6
MAmmoTH2-7B-Plus
- 53.5 freewheelin/free-solar-evo-v0.11 📑
- 53.3 Artples/L-MChat-7b 📑
- 53.3 vaiv/GeM2-Llamion-14B-Chat 📑
- 53.2 abacusai/bigyi-15b 📑
- 53.1 vicgalle/ConfigurableHermes-7B 📑
- 53.0 freewheelin/free-solar-evo-v0.1 📑
- 53.0
Yi 6B
- 52.8 Qwen/Qwen1.5-MoE-A2.7B-Chat 📑
- 52.7 MoaData/Myrrh_solar_10.7b_3.0 📑
- 52.7 winninghealth/WiNGPT2-Llama-3-8B-Base 📑
- 52.6 FlagAlpha/Llama3-Chinese-8B-Instruct 📑
- 52.5 migtissera/Tess-2.0-Llama-3-8B 📑
- 52.4 shanchen/llama3-8B-slerp-med-chinese 📑
- 52.3 MTSAIR/multi_verse_model 📑
- 52.3 SeaLLMs/SeaLLM-7B-v2 📑
- 51.9 tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1 📑
- 51.6 UnicomLLM/Unichat-llama3-Chinese-8B 📑
- 51.5
Qwen2-1.5B-Instruct
- 51.5 vaiv/GeM2-Llamion-14B-LongChat 📑
- 51.4
Qwen1.5-4B-Chat
- 51.4 freewheelin/free-llama3-dpo-v0.2 📑
- 51.3 rombodawg/Everyone-Coder-4x7b-Base 📑
- 51.3 chujiezheng/Starling-LM-7B-alpha-ExPO 📑
- 51.2 refuelai/Llama-3-Refueled 📑
- 50.9 speakleash/Bielik-11B-v2.3-Instruct 📑
- 50.9 upstage/SOLAR-10.7B-v1.0 📑
- 50.9 vicgalle/Configurable-Janus-7B 📑
- 50.8 Qwen/Qwen1.5-4B 📑
- 50.7 UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 📑
- 50.4 internlm/internlm2-base-7b 📑
- 50.4 GritLM/GritLM-7B-KTO 📑
- 50.3 UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3 📑
- 50.2 kaist-ai/janus-dpo-7b 📑
- 50.1 scb10x/llama-3-typhoon-v1.5-8b-instruct 📑
- 50.1
phi-3-mini 3.8B
- 50.0 rombodawg/rombos_Replete-Coder-Llama3-8B 📑
- 50.0 beowolx/CodeNinja-1.0-OpenChat-7B 📑
- 49.9 dfurman/Llama-3-8B-Orpo-v0.1 📑
- 49.8 kaist-ai/mistral-orpo-capybara-7k 📑
- 49.6 cognitivecomputations/dolphin-2.9.1-llama-3-8b 📑
- 49.5 kaist-ai/janus-7b 📑
- 49.4 ChatGLM3-6B
- 49.4 nvidia/Llama3-ChatQA-1.5-8B 📑
- 49.4 openbmb/MiniCPM-2B-sft-bf16 📑
- 49.3 hfl/chinese-alpaca-2-13b 📑
- 49.2
Qwen2-1.5B
- 49.1 AIJUUD/juud-Mistral-7B-dpo 📑
- 49.0
Mistral-7B-Instruct-v0.2
- 49.0
Phi-3-mini-128k-instruct
- 48.9 uukuguy/speechless-zephyr-code-functionary-7b 📑
- 48.9 01-ai/Yi-Coder-9B-Chat 📑
- 48.9 uukuguy/speechless-code-mistral-7b-v1.0 📑
- 48.8 abacusai/bigstral-12b-32k 📑
- 48.6 chujiezheng/Mistral7B-PairRM-SPPO-ExPO 📑
- 48.5 shanchen/llama3-8B-slerp-biomed-chat-chinese 📑
- 48.4 01-ai/Yi-Coder-9B 📑
- 47.8 vicgalle/Configurable-Mistral-7B 📑
- 47.5 oobabooga/CodeBooga-34B-v0.1 📑
- 47.5 kaist-ai/janus-orpo-7b 📑
- 47.5
Mistral 7B v0.1
- 47.3 royallab/ZephRP-m7b 📑
- 46.6 maywell/Synatra-7B-v0.3-RP 📑
- 46.5 hfl/chinese-alpaca-2-13b-16k 📑
- 45.7 cognitivecomputations/dolphin-2.6-mixtral-8x7b 📑
- 45.2 deepseek-ai/deepseek-llm-7b-base 📑
- 45.2 aws-prototyping/MegaBeam-Mistral-7B-512k 📑
- 44.7 amazon/MegaBeam-Mistral-7B-300k 📑
- 44.6 SenseLLM/ReflectionCoder-DS-33B 📑
- 44.5 Azure99/blossom-v5.1-9b 📑
- 43.8 hfl/chinese-llama-2-13b 📑
- 43.6 Qwen/Qwen1.5-1.8B-Chat 📑
- 43.1 SenseLLM/ReflectionCoder-CL-34B 📑
- 42.9 Infinirc/Infinirc-Llama3-8B-2G-Release-v1.0 📑
- 42.5 UnicomLLM/Unichat-llama3-Chinese-8B-28K 📑
- 42.4 hfl/chinese-llama-2-13b-16k 📑
- 41.7 haoranxu/ALMA-13B-Pretrain 📑
- 41.7 Qwen/Qwen1.5-1.8B 📑
- 41.3 scb10x/llama-3-typhoon-v1.5-8b 📑
- 40.6 haoranxu/ALMA-13B-R 📑
- 40.0
Qwen2-0.5B-Instruct
- 39.9 deepseek-ai/deepseek-coder-6.7b-instruct 📑
- 39.6 OpenBuddy/openbuddy-mistral-22b-v21.1-32k 📑
- 38.6
Qwen2-0.5B
- 38.5 SeaLLMs/SeaLLM-7B-v2.5 📑
- 36.7 Qwen/Qwen1.5-0.5B-Chat 📑
- 36.4 haoranxu/ALMA-7B-R 📑
- 35.8 Qwen/Qwen1.5-0.5B 📑
- 35.0 cognitivecomputations/dolphin-2.9.1-mixtral-1x22b 📑
- 34.4 RLHFlow/ArmoRM-Llama3-8B-v0.1 📑
- 34.3
Gemma 1.1 2B IT
- 33.8
Gemma 2B
- 33.4
Gemma 7B
- 33.1
Phi-2
- 32.4 Artples/L-MChat-Small 📑
- 30.7
Phi-1.5
- 30.2 deepseek-ai/deepseek-coder-1.3b-instruct 📑
- 1
Qwen2-72B 75.7
- 2 freewheelin/free-evo-qwen72b-v0.8-re 📑 has been flagged! See discussion #510 74.6
- 3 davidkim205/Rhea-72b-v0.5 📑 74.3
- 4 paloalma/TW3-JRGL-v2 📑 73.3
- 5 abacusai/Smaug-72B-v0.1 📑 73.2
- 6 MTSAIR/MultiVerse_70B 📑 72.1
- 7 paloalma/Le_Triomphant-ECE-TW3 📑 72.0
- 8 saltlux/luxia-21.4b-alignment-v1.0 📑 71.7
- 9 paloalma/ECE-TW3-JRGL-V5 📑 71.2
- 10 CombinHorizon/YiSM-blossom5.1-34B-SLERP 📑 70.9
- 11 Weyaxi/Bagel-Hermes-34B-Slerp 📑 70.8
- 12 fblgit/UNA-SimpleSmaug-34b-v1beta 📑 70.7
- 13 abacusai/Smaug-34B-v0.1 📑 70.6
- 14 cloudyu/Yi-34Bx2-MoE-60B-DPO 📑 70.6
- 15
Qwen1.5-72B 70.5
- 16 cloudyu/Yi-34Bx2-MoE-60B 📑 70.4
- 17 ConvexAI/Luminex-34B-v0.2 📑 70.4
- 18 ConvexAI/Luminex-34B-v0.1 📑 70.3
- 19 cloudyu/Yi-34Bx2-MOE-200K 📑 69.6
- 20 OpenBuddy/openbuddy-yi1.5-34b-v21.3-32k 📑 69.6
- 21 saltlux/luxia-21.4b-alignment-v1.2 📑 69.4
- 22 cloudyu/Mixtral_34Bx2_MoE_60B 📑 69.4
- 23 migtissera/Llama-3-70B-Synthia-v3.5 📑 69.4
- 24 bosonai/Higgs-Llama-3-70B 📑 69.4
- 25 jondurbin/bagel-dpo-34b-v0.2 📑 69.4
- 26 OpenBuddy/openbuddy-deepseek-67b-v18.1-4k 📑 69.3
- 27 abacusai/Smaug-Llama-3-70B-Instruct 📑 69.1
- 28 01-ai/Yi-1.5-34B-Chat 📑 68.9
- 29 OpenBuddy/openbuddy-llama3-70b-v21.2-32k 📑 68.9
- 30 Qwen/Qwen2-57B-A14B-Instruct 📑 68.7
- 31 Azure99/blossom-v5.1-34b 📑 68.7
- 32 altomek/YiSM-34B-0rn 📑 68.4
- 33 gbueno86/Meta-LLama-3-Cat-Smaug-LLama-70b 📑 68.4
- 34 migtissera/Tess-2.0-Llama-3-70B 📑 67.9
- 35 tenyx/Llama3-TenyxChat-70B 📑 67.9
- 36 cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 📑 67.8
- 37 wenbopan/Faro-Yi-34B-DPO 📑 67.8
- 38 OpenBuddy/openbuddy-zero-56b-v21.2-32k 📑 67.6
- 39 chujiezheng/Llama3-70B-Chinese-Chat-ExPO 📑 67.6
- 40 chujiezheng/Smaug-34B-v0.1-ExPO 📑 67.5
- 41 MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2 📑 67.5
- 42 failspy/Smaug-Llama-3-70B-Instruct-abliterated-v3 📑 67.5
- 43 cognitivecomputations/dolphin-2.9.1-yi-1.5-34b 📑 67.5
- 44 failspy/llama-3-70B-Instruct-abliterated 📑 67.3
- 45 Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 📑 67.3
- 46 brucethemoose/Yi-34B-200K-DARE-merge-v7 📑 67.1
- 47 abacusai/Smaug-Llama-3-70B-Instruct-32K 📑 67.0
- 48 chujiezheng/Smaug-Llama-3-70B-Instruct-ExPO 📑 67.0
- 49 01-ai/Yi-1.5-34B-Chat-16K 📑 66.9
- 50 01-ai/Yi-1.5-34B-32K 📑 66.8
- 51
Yi-1.5-34B 66.7
- 52
Qwen1.5-32B 66.6
- 53 gbueno86/Meta-LLama-3-Cat-A-LLama-70b 📑 66.6
- 54 Qwen/Qwen2-57B-A14B 📑 66.5
- 55 mmnga/Llama-3-70B-japanese-suzume-vector-v0.1 📑 66.2
- 56 cognitivecomputations/dolphin-2.9.1-llama-3-70b 📑 66.1
- 57
Qwen1.5-14B-Chat 66.0
- 58 Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO 📑 65.7
- 59 BAAI/Infinity-Instruct-3M-0625-Yi-1.5-9B 📑 65.6
- 60 VAGOsolutions/SauerkrautLM-Phi-3-medium 📑 65.4
- 61
Yi-34B 65.3
- 62 ValiantLabs/Llama3-70B-ShiningValiant2 📑 65.3
- 63 wenbopan/Faro-Yi-34B 📑 65.2
- 64 CausalLM/34b-beta 📑 64.7
- 65 OpenBuddy/openbuddy-yi1.5-34b-v21.6-32k-fp16 📑 64.6
- 66 wenbopan/Faro-Yi-9B-DPO 📑 64.4
- 67 deepseek-ai/deepseek-llm-67b-base 📑 64.4
- 68
Yi-1.5-9B-Chat 64.3
- 69 Duxiaoman-DI/XuanYuan-70B 📑 64.2
- 70
WizardLM-2 8x22B 64.2
- 71 vicgalle/Configurable-Yi-1.5-9B-Chat 📑 64.0
- 72 cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k 📑 64.0
- 73 internlm/internlm2-20b 📑 63.9
- 74 NousResearch/Nous-Hermes-2-Yi-34B 📑 63.9
- 75 NLPark/AnFeng_v3_Avocet 📑 63.7
- 76
Qwen2-7B 63.5
- 77 byroneverson/Yi-1.5-9B-Chat-16K-abliterated 📑 63.5
- 78 jondurbin/bagel-dpo-34b-v0.5 📑 63.4
- 79 paloalma/ECE-TW3-JRGL-V1 📑 63.3
- 80
MAmmoTH2-8x7B-Plus 63.2
- 81 OpenBuddy/openbuddy-yi1.5-9b-v21.1-32k 📑 63.0
- 82 byroneverson/Yi-1.5-9B-Chat-abliterated 📑 62.9
- 83 NLPark/Shi-Ci_v3-Robin 📑 62.9
- 84 cognitivecomputations/dolphin-2.9.1-yi-1.5-9b 📑 62.9
- 85 wenbopan/Faro-Yi-9B 📑 62.9
- 86 qnguyen3/Master-Yi-9B 📑 62.6
- 87 Qwen/Qwen1.5-32B-Chat 📑 62.6
- 88 01-ai/Yi-1.5-9B-Chat-16K 📑 62.5
- 89 cognitivecomputations/dolphin-2.9.2-mixtral-8x22b 📑 62.4
- 90 duoqi/Nanbeige2-16B-Chat 📑 62.4
- 91 01-ai/Yi-1.5-9B-32K 📑 61.9
- 92 01-ai/Yi-1.5-9B 📑 61.8
- 93
Qwen2-7B-Instruct 61.8
- 94
Qwen1.5-14B 61.6
- 95 chujiezheng/internlm2-chat-20b-ExPO 📑 61.3
- 96 migtissera/Tess-2.0-Llama-3-70B-v0.2 📑 61.2
- 97 failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5 📑 60.9
- 98 migtissera/Tess-M-v1.3 📑 60.9
- 99 ValiantLabs/Llama3-70B-Fireplace 📑 60.8
- 100 BAAI/Infinity-Instruct-7M-0729-Llama3_1-8B 📑 60.6
- 101 byroneverson/Mistral-Small-Instruct-2409-abliterated 📑 60.5
- 102 internlm/internlm2-chat-7b 📑 60.5
- 103 Duxiaoman-DI/XuanYuan-70B-Chat 📑 60.5
- 104 internlm/internlm2-chat-20b 📑 60.2
- 105 xiangxinai/Xiangxin-2XL-Chat-1048k-Chinese-Llama3-70B 📑 60.2
- 106 Nous-Hermes-2-Mixtral-8x7B-DPO 60.2
- 107 sophosympatheia/Midnight-Miqu-70B-v1.5 📑 60.1
- 108 GritLM/GritLM-8x7B-KTO 📑 60.1
- 109 BAAI/Infinity-Instruct-3M-0625-Llama3-8B 📑 59.8
- 110 internlm/internlm2-7b 📑 59.8
- 111 Langboat/Mengzi3-8B-Chat 📑 59.7
- 112 chujiezheng/LLaMA3-iterative-DPO-final-ExPO 📑 59.7
- 113 CofeAI/Tele-FLM 📑 59.6
- 114 internlm/internlm2-base-20b 📑 59.6
- 115 01-ai/Yi-34B-Chat 📑 59.4
- 116 cognitivecomputations/dolphin-2.9.2-Phi-3-Medium 📑 59.3
- 117 vicgalle/CarbonBeagle-11B-truthy 📑 59.2
- 118 abhishek/autotrain-llama3-70b-orpo-v1 📑 59.1
- 119 shenzhi-wang/Llama3-8B-Chinese-Chat 📑 59.0
- 120 NotAiLOL/Yi-1.5-dolphin-9B 📑 58.9
- 121 vicgalle/CarbonBeagle-11B 📑 58.7
- 122 DeepMount00/Llama-3-8b-Ita 📑 58.7
- 123 VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct 📑 58.7
- 124 MaziyarPanahi/Llama-3-8B-Instruct-v0.8 📑 58.6
- 125 Kukedlc/NeuralLLaMa-3-8b-DT-v0.1 📑 58.6
- 126 GritLM/GritLM-8x7B 📑 58.5
- 127 mlabonne/Daredevil-8B-abliterated 📑 58.5
- 128 jondurbin/airoboros-70b-3.3 📑 58.5
- 129 yaojialzc/Gigi-Llama3-8B-Chinese-zh 📑 58.4
- 130 BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B 📑 58.4
- 131 jondurbin/airoboros-dpo-70b-3.3 📑 58.4
- 132 turboderp/Cat-Llama-3-70B-instruct 📑 58.4
- 133 Yi-9B 58.3
- 134 MaziyarPanahi/Llama-3-8B-Instruct-v0.10 📑 58.3
- 135 cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated 📑 58.3
- 136 mlabonne/NeuralDaredevil-8B-abliterated 📑 58.3
- 137 haoranxu/Llama-3-Instruct-8B-SimPO 📑 58.1
- 138 01-ai/Yi-9B-200K 📑 58.1
- 139 grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge 📑 58.0
- 140 OpenBuddy/openbuddy-llama3-8b-v21.2-32k 📑 58.0
- 141 vicgalle/ConfigurableBeagle-11B 📑 58.0
- 142 Danielbrdz/Barcenas-Llama3-8b-ORPO 📑 58.0
- 143 MaziyarPanahi/Llama-3-8B-Instruct-v0.9 📑 58.0
- 144 UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 📑 57.9
- 145 01-ai/Yi-34B-200K 📑 57.9
- 146 Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 📑 57.9
- 147 UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2 📑 57.8
- 148 mixtao/MixTAO-7Bx2-MoE-v8.1 📑 57.7
- 149 shadowml/BeagSake-7B 📑 57.7
- 150 shadowml/Mixolar-4x7b 📑 57.7
- 151 jeonsworld/CarbonVillain-en-10.7B-v4 📑 57.6
- 152 kekmodel/StopCarbon-10.7B-v5 📑 57.6
- 153 hfl/chinese-mixtral-instruct 📑 57.6
- 154 haoranxu/Llama-3-Instruct-8B-CPO-SimPO 📑 57.5
- 155 NLPark/Test1_SLIDE 📑 57.5
- 156 hfl/llama-3-chinese-8b-instruct-v2 📑 57.4
- 157 invalid-coder/Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp 📑 57.4
- 158 zhengr/MixTAO-7Bx2-MoE-v8.1 📑 57.3
- 159 dzakwan/dzakwan-MoE-4x7b-Beta 📑 57.3
- 160 RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2 📑 57.3
- 161 hfl/llama-3-chinese-8b-instruct-v3 📑 57.3
- 162 Magpie-Align/Llama-3-8B-Magpie-Align-v0.3 📑 57.2
- 163 ghost-x/ghost-8b-beta-1608 📑 57.2
- 164
SOLAR-10.7B-Instruct-v1.0 57.2
- 165 chujiezheng/Llama3-8B-Chinese-Chat-ExPO 📑 57.2
- 166 uygarkurt/llama-3-merged-linear 📑 57.2
- 167 jondurbin/bagel-8b-v1.0 📑 57.0
- 168 jsfs11/MixtureofMerges-MoE-4x7b-v5 📑 57.0
- 169 mlabonne/ChimeraLlama-3-8B-v3 📑 57.0
- 170
Yi-6B-Chat 57.0
- 171 Kukedlc/NeuralSynthesis-7B-v0.3 📑 57.0
- 172 mlabonne/AlphaMonarch-7B 📑 56.9
- 173 mlabonne/ChimeraLlama-3-8B-v2 📑 56.9
- 174 Kquant03/CognitiveFusion2-4x7B-BF16 📑 56.9
- 175 meraGPT/mera-mix-4x7B 📑 56.8
- 176 ibivibiv/multimaster-7b-v6 📑 56.8
- 177 vicgalle/Configurable-Llama-3-8B-v0.3 📑 56.8
- 178 Kukedlc/NeuralSynthesis-7B-v0.1 📑 56.7
- 179 yunconglong/DARE_TIES_13B 📑 56.7
- 180 mlabonne/NeuralMonarch-7B 📑 56.7
- 181 yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 📑 56.7
- 182 yunconglong/MoE_13B_DPO 📑 56.7
- 183 Kukedlc/NeuralSynthesis-7b-v0.4-slerp 📑 56.7
- 184 cognitivecomputations/WestLake-7B-v2-laser 📑 56.7
- 185 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half 📑 56.7
- 186 MaziyarPanahi/Calme-4x7B-MoE-v0.1 📑 56.6
- 187 grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge 📑 56.6
- 188 allknowingroger/MultiverseEx26-7B-slerp 📑 56.6
- 189 vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B 📑 56.6
- 190 jsfs11/MixtureofMerges-MoE-4x7b-v4 📑 56.6
- 191 Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3 📑 56.6
- 192 automerger/YamshadowExperiment28-7B 📑 56.6
- 193
Qwen1.5-7B 56.6
- 194 NousResearch/Hermes-2-Theta-Llama-3-8B 📑 has been flagged! See discussion #510 56.6
- 195 MaziyarPanahi/Calme-4x7B-MoE-v0.2 📑 56.5
- 196
MAmmoTH2-8B-Plus 56.4
- 197 CultriX/NeuralMona_MoE-4x7B 📑 56.4
- 198 hfl/llama-3-chinese-8b-instruct 📑 56.3
- 199 winninghealth/WiNGPT2-Llama-3-8B-Chat 📑 56.3
- 200 ibivibiv/llama-3-nectar-dpo-8B 📑 56.3
- 201 mlabonne/Beyonder-4x7B-v3 📑 56.3
- 202 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25 📑 56.3
- 203 chujiezheng/internlm2-chat-7b-ExPO 📑 56.2
- 204 Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4 📑 56.2
- 205 failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 📑 56.1
- 206 01-ai/Yi-1.5-6B 📑 56.0
- 207 lightblue/suzume-llama-3-8B-multilingual 📑 56.0
- 208 Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5 📑 56.0
- 209 MaziyarPanahi/Topxtral-4x7B-v0.1 📑 55.9
- 210 chujiezheng/tulu-2-dpo-70b-ExPO 📑 55.9
- 211 abacusai/Smaug-Mixtral-v0.1 📑 55.8
- 212 princeton-nlp/Llama-3-8B-ProLong-512k-Instruct 📑 55.8
- 213 vaiv/GeM2-Llamion-14B-Base 📑 55.7
- 214 OpenBuddy/openbuddy-zero-14b-v22.3-32k 📑 55.6
- 215 openchat/openchat-3.6-8b-20240522 📑 55.6
- 216 eldogbbhed/Peagle-9b 📑 55.5
- 217 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75 📑 55.4
- 218 abacusai/Slerp-CM-mist-dpo 📑 55.3
- 219 migtissera/Llama-3-8B-Synthia-v3.5 📑 55.2
- 220 failspy/Codestral-22B-v0.1-abliterated-v3 📑 55.1
- 221 NousResearch/Meta-Llama-3-8B-Instruct 📑 55.1
- 222 duoqi/Nanbeige-16B-Base-Llama 📑 55.0
- 223 princeton-nlp/Llama-3-8B-ProLong-64k-Instruct 📑 54.9
- 224 Qwen/Qwen1.5-MoE-A2.7B 📑 54.8
- 225 NousResearch/Nous-Hermes-2-SOLAR-10.7B 📑 54.8
- 226 HIT-SCIR/Chinese-Mixtral-8x7B 📑 54.7
- 227 hfl/chinese-mixtral 📑 54.6
- 228 princeton-nlp/Llama-3-8B-ProLong-64k-Base 📑 54.6
- 229 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full 📑 54.6
- 230 rombodawg/rombos_Replete-Coder-Instruct-8b-Merged 📑 54.5
- 231 liminerity/M7-7b 📑 54.5
- 232 deepseek-ai/deepseek-llm-7b-chat 📑 54.3
- 233 princeton-nlp/Llama-3-8B-ProLong-512k-Base 📑 54.1
- 234 Weyaxi/Einstein-v6.1-Llama3-8B 📑 54.1
- 235 cognitivecomputations/openchat-3.5-0106-laser 📑 53.8
- 236 openchat/openchat-3.5-0106 📑 53.7
- 237 chujiezheng/Starling-LM-7B-beta-ExPO 📑 53.7
- 238 freewheelin/free-solar-evo-v0.13 📑 53.7
- 239 abacusai/Llama-3-Smaug-8B 📑 53.7
- 240 cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2 📑 53.6
- 241
MAmmoTH2-7B-Plus 53.6
- 242 freewheelin/free-solar-evo-v0.11 📑 53.5
- 243 Artples/L-MChat-7b 📑 53.3
- 244 vaiv/GeM2-Llamion-14B-Chat 📑 53.3
- 245 abacusai/bigyi-15b 📑 53.2
- 246 vicgalle/ConfigurableHermes-7B 📑 53.1
- 247 freewheelin/free-solar-evo-v0.1 📑 53.0
- 248
Yi 6B 53.0
- 249 Qwen/Qwen1.5-MoE-A2.7B-Chat 📑 52.8
- 250 MoaData/Myrrh_solar_10.7b_3.0 📑 52.7
- 251 winninghealth/WiNGPT2-Llama-3-8B-Base 📑 52.7
- 252 FlagAlpha/Llama3-Chinese-8B-Instruct 📑 52.6
- 253 migtissera/Tess-2.0-Llama-3-8B 📑 52.5
- 254 shanchen/llama3-8B-slerp-med-chinese 📑 52.4
- 255 MTSAIR/multi_verse_model 📑 52.3
- 256 SeaLLMs/SeaLLM-7B-v2 📑 52.3
- 257 tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1 📑 51.9
- 258 UnicomLLM/Unichat-llama3-Chinese-8B 📑 51.6
- 259
Qwen2-1.5B-Instruct 51.5
- 260 vaiv/GeM2-Llamion-14B-LongChat 📑 51.5
- 261
Qwen1.5-4B-Chat 51.4
- 262 freewheelin/free-llama3-dpo-v0.2 📑 51.4
- 263 rombodawg/Everyone-Coder-4x7b-Base 📑 51.3
- 264 chujiezheng/Starling-LM-7B-alpha-ExPO 📑 51.3
- 265 refuelai/Llama-3-Refueled 📑 51.2
- 266 speakleash/Bielik-11B-v2.3-Instruct 📑 50.9
- 267 upstage/SOLAR-10.7B-v1.0 📑 50.9
- 268 vicgalle/Configurable-Janus-7B 📑 50.9
- 269 Qwen/Qwen1.5-4B 📑 50.8
- 270 UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 📑 50.7
- 271 internlm/internlm2-base-7b 📑 50.4
- 272 GritLM/GritLM-7B-KTO 📑 50.4
- 273 UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3 📑 50.3
- 274 kaist-ai/janus-dpo-7b 📑 50.2
- 275 scb10x/llama-3-typhoon-v1.5-8b-instruct 📑 50.1
- 276
phi-3-mini 3.8B 50.1
- 277 rombodawg/rombos_Replete-Coder-Llama3-8B 📑 50.0
- 278 beowolx/CodeNinja-1.0-OpenChat-7B 📑 50.0
- 279 dfurman/Llama-3-8B-Orpo-v0.1 📑 49.9
- 280 kaist-ai/mistral-orpo-capybara-7k 📑 49.8
- 281 cognitivecomputations/dolphin-2.9.1-llama-3-8b 📑 49.6
- 282 kaist-ai/janus-7b 📑 49.5
- 283 ChatGLM3-6B 49.4
- 284 nvidia/Llama3-ChatQA-1.5-8B 📑 49.4
- 285 openbmb/MiniCPM-2B-sft-bf16 📑 49.4
- 286 hfl/chinese-alpaca-2-13b 📑 49.3
- 287
Qwen2-1.5B 49.2
- 288 AIJUUD/juud-Mistral-7B-dpo 📑 49.1
- 289
Mistral-7B-Instruct-v0.2 49.0
- 290
Phi-3-mini-128k-instruct 49.0
- 291 uukuguy/speechless-zephyr-code-functionary-7b 📑 48.9
- 292 01-ai/Yi-Coder-9B-Chat 📑 48.9
- 293 uukuguy/speechless-code-mistral-7b-v1.0 📑 48.9
- 294 abacusai/bigstral-12b-32k 📑 48.8
- 295 chujiezheng/Mistral7B-PairRM-SPPO-ExPO 📑 48.6
- 296 shanchen/llama3-8B-slerp-biomed-chat-chinese 📑 48.5
- 297 01-ai/Yi-Coder-9B 📑 48.4
- 298 vicgalle/Configurable-Mistral-7B 📑 47.8
- 299 oobabooga/CodeBooga-34B-v0.1 📑 47.5
- 300 kaist-ai/janus-orpo-7b 📑 47.5
- 301
Mistral 7B v0.1 47.5
- 302 royallab/ZephRP-m7b 📑 47.3
- 303 maywell/Synatra-7B-v0.3-RP 📑 46.6
- 304 hfl/chinese-alpaca-2-13b-16k 📑 46.5
- 305 cognitivecomputations/dolphin-2.6-mixtral-8x7b 📑 45.7
- 306 deepseek-ai/deepseek-llm-7b-base 📑 45.2
- 307 aws-prototyping/MegaBeam-Mistral-7B-512k 📑 45.2
- 308 amazon/MegaBeam-Mistral-7B-300k 📑 44.7
- 309 SenseLLM/ReflectionCoder-DS-33B 📑 44.6
- 310 Azure99/blossom-v5.1-9b 📑 44.5
- 311 hfl/chinese-llama-2-13b 📑 43.8
- 312 Qwen/Qwen1.5-1.8B-Chat 📑 43.6
- 313 SenseLLM/ReflectionCoder-CL-34B 📑 43.1
- 314 Infinirc/Infinirc-Llama3-8B-2G-Release-v1.0 📑 42.9
- 315 UnicomLLM/Unichat-llama3-Chinese-8B-28K 📑 42.5
- 316 hfl/chinese-llama-2-13b-16k 📑 42.4
- 317 haoranxu/ALMA-13B-Pretrain 📑 41.7
- 318 Qwen/Qwen1.5-1.8B 📑 41.7
- 319 scb10x/llama-3-typhoon-v1.5-8b 📑 41.3
- 320 haoranxu/ALMA-13B-R 📑 40.6
- 321
Qwen2-0.5B-Instruct 40.0
- 322 deepseek-ai/deepseek-coder-6.7b-instruct 📑 39.9
- 323 OpenBuddy/openbuddy-mistral-22b-v21.1-32k 📑 39.6
- 324
Qwen2-0.5B 38.6
- 325 SeaLLMs/SeaLLM-7B-v2.5 📑 38.5
- 326 Qwen/Qwen1.5-0.5B-Chat 📑 36.7
- 327 haoranxu/ALMA-7B-R 📑 36.4
- 328 Qwen/Qwen1.5-0.5B 📑 35.8
- 329 cognitivecomputations/dolphin-2.9.1-mixtral-1x22b 📑 35.0
- 330 RLHFlow/ArmoRM-Llama3-8B-v0.1 📑 34.4
- 331
Gemma 1.1 2B IT 34.3
- 332
Gemma 2B 33.8
- 333
Gemma 7B 33.4
- 334
Phi-2 33.1
- 335 Artples/L-MChat-Small 📑 32.4
- 336
Phi-1.5 30.7
- 337 deepseek-ai/deepseek-coder-1.3b-instruct 📑 30.2
Source: Official Open Chinese LLM Leaderboard leaderboard
- 75.7
Qwen2-72B
- 70.5
Qwen1.5-72B
- 66.7
Yi-1.5-34B
- 66.6
Qwen1.5-32B
- 66.0
Qwen1.5-14B-Chat
- 65.3
Yi-34B
- 64.3
Yi-1.5-9B-Chat
- 64.2
WizardLM-2 8x22B
- 63.5
Qwen2-7B
- 63.2
MAmmoTH2-8x7B-Plus
- 61.8
Qwen2-7B-Instruct
- 61.6
Qwen1.5-14B
- 60.2 Nous-Hermes-2-Mixtral-8x7B-DPO
- 58.3 Yi-9B
- 57.2
SOLAR-10.7B-Instruct-v1.0
- 57.0
Yi-6B-Chat
- 56.6
Qwen1.5-7B
- 56.4
MAmmoTH2-8B-Plus
- 53.6
MAmmoTH2-7B-Plus
- 53.0
Yi 6B
- 51.5
Qwen2-1.5B-Instruct
- 51.4
Qwen1.5-4B-Chat
- 50.1
phi-3-mini 3.8B
- 49.4 ChatGLM3-6B
- 49.2
Qwen2-1.5B
- 49.0
Mistral-7B-Instruct-v0.2
- 49.0
Phi-3-mini-128k-instruct
- 47.5
Mistral 7B v0.1
- 40.0
Qwen2-0.5B-Instruct
- 38.6
Qwen2-0.5B
- 34.3
Gemma 1.1 2B IT
- 33.8
Gemma 2B
- 33.4
Gemma 7B
- 33.1
Phi-2
- 30.7
Phi-1.5
- 1
Qwen2-72B 75.7
- 2
Qwen1.5-72B 70.5
- 3
Yi-1.5-34B 66.7
- 4
Qwen1.5-32B 66.6
- 5
Qwen1.5-14B-Chat 66.0
- 6
Yi-34B 65.3
- 7
Yi-1.5-9B-Chat 64.3
- 8
WizardLM-2 8x22B 64.2
- 9
Qwen2-7B 63.5
- 10
MAmmoTH2-8x7B-Plus 63.2
- 11
Qwen2-7B-Instruct 61.8
- 12
Qwen1.5-14B 61.6
- 13 Nous-Hermes-2-Mixtral-8x7B-DPO 60.2
- 14 Yi-9B 58.3
- 15
SOLAR-10.7B-Instruct-v1.0 57.2
- 16
Yi-6B-Chat 57.0
- 17
Qwen1.5-7B 56.6
- 18
MAmmoTH2-8B-Plus 56.4
- 19
MAmmoTH2-7B-Plus 53.6
- 20
Yi 6B 53.0
- 21
Qwen2-1.5B-Instruct 51.5
- 22
Qwen1.5-4B-Chat 51.4
- 23
phi-3-mini 3.8B 50.1
- 24 ChatGLM3-6B 49.4
- 25
Qwen2-1.5B 49.2
- 26
Mistral-7B-Instruct-v0.2 49.0
- 27
Phi-3-mini-128k-instruct 49.0
- 28
Mistral 7B v0.1 47.5
- 29
Qwen2-0.5B-Instruct 40.0
- 30
Qwen2-0.5B 38.6
- 31
Gemma 1.1 2B IT 34.3
- 32
Gemma 2B 33.8
- 33
Gemma 7B 33.4
- 34
Phi-2 33.1
- 35
Phi-1.5 30.7
Source: Official Open Chinese LLM Leaderboard leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 75.7 | Jun 2024 | Official leaderboard | |
| 2 | freewheelin/free-evo-qwen72b-v0.8-re 📑 has been flagged! See discussion #510 | 74.6 | Official leaderboard | ||
| 3 | davidkim205/Rhea-72b-v0.5 📑 | 74.3 | Official leaderboard | ||
| 4 | paloalma/TW3-JRGL-v2 📑 | 73.3 | Official leaderboard | ||
| 5 | abacusai/Smaug-72B-v0.1 📑 | 73.2 | Official leaderboard | ||
| 6 | MTSAIR/MultiVerse_70B 📑 | 72.1 | Official leaderboard | ||
| 7 | paloalma/Le_Triomphant-ECE-TW3 📑 | 72.0 | Official leaderboard | ||
| 8 | saltlux/luxia-21.4b-alignment-v1.0 📑 | 71.7 | Official leaderboard | ||
| 9 | paloalma/ECE-TW3-JRGL-V5 📑 | 71.2 | Official leaderboard | ||
| 10 | CombinHorizon/YiSM-blossom5.1-34B-SLERP 📑 | 70.9 | Official leaderboard | ||
| 11 | Weyaxi/Bagel-Hermes-34B-Slerp 📑 | 70.8 | Official leaderboard | ||
| 12 | fblgit/UNA-SimpleSmaug-34b-v1beta 📑 | 70.7 | Official leaderboard | ||
| 13 | abacusai/Smaug-34B-v0.1 📑 | 70.6 | Official leaderboard | ||
| 14 | cloudyu/Yi-34Bx2-MoE-60B-DPO 📑 | 70.6 | Official leaderboard | ||
| 15 | | 70.5 | Feb 2024 | Official leaderboard | |
| 16 | cloudyu/Yi-34Bx2-MoE-60B 📑 | 70.4 | Official leaderboard | ||
| 17 | ConvexAI/Luminex-34B-v0.2 📑 | 70.4 | Official leaderboard | ||
| 18 | ConvexAI/Luminex-34B-v0.1 📑 | 70.3 | Official leaderboard | ||
| 19 | cloudyu/Yi-34Bx2-MOE-200K 📑 | 69.6 | Official leaderboard | ||
| 20 | OpenBuddy/openbuddy-yi1.5-34b-v21.3-32k 📑 | 69.6 | Official leaderboard | ||
| 21 | saltlux/luxia-21.4b-alignment-v1.2 📑 | 69.4 | Official leaderboard | ||
| 22 | cloudyu/Mixtral_34Bx2_MoE_60B 📑 | 69.4 | Official leaderboard | ||
| 23 | migtissera/Llama-3-70B-Synthia-v3.5 📑 | 69.4 | Official leaderboard | ||
| 24 | bosonai/Higgs-Llama-3-70B 📑 | 69.4 | Official leaderboard | ||
| 25 | jondurbin/bagel-dpo-34b-v0.2 📑 | 69.4 | Official leaderboard | ||
| 26 | OpenBuddy/openbuddy-deepseek-67b-v18.1-4k 📑 | 69.3 | Official leaderboard | ||
| 27 | abacusai/Smaug-Llama-3-70B-Instruct 📑 | 69.1 | Official leaderboard | ||
| 28 | 01-ai/Yi-1.5-34B-Chat 📑 | 68.9 | Official leaderboard | ||
| 29 | OpenBuddy/openbuddy-llama3-70b-v21.2-32k 📑 | 68.9 | Official leaderboard | ||
| 30 | Qwen/Qwen2-57B-A14B-Instruct 📑 | 68.7 | Official leaderboard | ||
| 31 | Azure99/blossom-v5.1-34b 📑 | 68.7 | Official leaderboard | ||
| 32 | altomek/YiSM-34B-0rn 📑 | 68.4 | Official leaderboard | ||
| 33 | gbueno86/Meta-LLama-3-Cat-Smaug-LLama-70b 📑 | 68.4 | Official leaderboard | ||
| 34 | migtissera/Tess-2.0-Llama-3-70B 📑 | 67.9 | Official leaderboard | ||
| 35 | tenyx/Llama3-TenyxChat-70B 📑 | 67.9 | Official leaderboard | ||
| 36 | cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16 📑 | 67.8 | Official leaderboard | ||
| 37 | wenbopan/Faro-Yi-34B-DPO 📑 | 67.8 | Official leaderboard | ||
| 38 | OpenBuddy/openbuddy-zero-56b-v21.2-32k 📑 | 67.6 | Official leaderboard | ||
| 39 | chujiezheng/Llama3-70B-Chinese-Chat-ExPO 📑 | 67.6 | Official leaderboard | ||
| 40 | chujiezheng/Smaug-34B-v0.1-ExPO 📑 | 67.5 | Official leaderboard | ||
| 41 | MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2 📑 | 67.5 | Official leaderboard | ||
| 42 | failspy/Smaug-Llama-3-70B-Instruct-abliterated-v3 📑 | 67.5 | Official leaderboard | ||
| 43 | cognitivecomputations/dolphin-2.9.1-yi-1.5-34b 📑 | 67.5 | Official leaderboard | ||
| 44 | failspy/llama-3-70B-Instruct-abliterated 📑 | 67.3 | Official leaderboard | ||
| 45 | Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 📑 | 67.3 | Official leaderboard | ||
| 46 | brucethemoose/Yi-34B-200K-DARE-merge-v7 📑 | 67.1 | Official leaderboard | ||
| 47 | abacusai/Smaug-Llama-3-70B-Instruct-32K 📑 | 67.0 | Official leaderboard | ||
| 48 | chujiezheng/Smaug-Llama-3-70B-Instruct-ExPO 📑 | 67.0 | Official leaderboard | ||
| 49 | 01-ai/Yi-1.5-34B-Chat-16K 📑 | 66.9 | Official leaderboard | ||
| 50 | 01-ai/Yi-1.5-34B-32K 📑 | 66.8 | Official leaderboard | ||
| 51 | | 66.7 | May 2024 | Official leaderboard | |
| 52 | | 66.6 | Feb 2024 | Official leaderboard | |
| 53 | gbueno86/Meta-LLama-3-Cat-A-LLama-70b 📑 | 66.6 | Official leaderboard | ||
| 54 | Qwen/Qwen2-57B-A14B 📑 | 66.5 | Official leaderboard | ||
| 55 | mmnga/Llama-3-70B-japanese-suzume-vector-v0.1 📑 | 66.2 | Official leaderboard | ||
| 56 | cognitivecomputations/dolphin-2.9.1-llama-3-70b 📑 | 66.1 | Official leaderboard | ||
| 57 | | 66.0 | Feb 2024 | Official leaderboard | |
| 58 | Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO 📑 | 65.7 | Official leaderboard | ||
| 59 | BAAI/Infinity-Instruct-3M-0625-Yi-1.5-9B 📑 | 65.6 | Official leaderboard | ||
| 60 | VAGOsolutions/SauerkrautLM-Phi-3-medium 📑 | 65.4 | Official leaderboard | ||
| 61 | | 65.3 | Nov 2023 | Official leaderboard | |
| 62 | ValiantLabs/Llama3-70B-ShiningValiant2 📑 | 65.3 | Official leaderboard | ||
| 63 | wenbopan/Faro-Yi-34B 📑 | 65.2 | Official leaderboard | ||
| 64 | CausalLM/34b-beta 📑 | 64.7 | Official leaderboard | ||
| 65 | OpenBuddy/openbuddy-yi1.5-34b-v21.6-32k-fp16 📑 | 64.6 | Official leaderboard | ||
| 66 | wenbopan/Faro-Yi-9B-DPO 📑 | 64.4 | Official leaderboard | ||
| 67 | deepseek-ai/deepseek-llm-67b-base 📑 | 64.4 | Official leaderboard | ||
| 68 | | 64.3 | May 2024 | Official leaderboard | |
| 69 | Duxiaoman-DI/XuanYuan-70B 📑 | 64.2 | Official leaderboard | ||
| 70 | | 64.2 | Apr 2024 | Official leaderboard | |
| 71 | vicgalle/Configurable-Yi-1.5-9B-Chat 📑 | 64.0 | Official leaderboard | ||
| 72 | cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k 📑 | 64.0 | Official leaderboard | ||
| 73 | internlm/internlm2-20b 📑 | 63.9 | Official leaderboard | ||
| 74 | NousResearch/Nous-Hermes-2-Yi-34B 📑 | 63.9 | Official leaderboard | ||
| 75 | NLPark/AnFeng_v3_Avocet 📑 | 63.7 | Official leaderboard | ||
| 76 | | 63.5 | Jun 2024 | Official leaderboard | |
| 77 | byroneverson/Yi-1.5-9B-Chat-16K-abliterated 📑 | 63.5 | Official leaderboard | ||
| 78 | jondurbin/bagel-dpo-34b-v0.5 📑 | 63.4 | Official leaderboard | ||
| 79 | paloalma/ECE-TW3-JRGL-V1 📑 | 63.3 | Official leaderboard | ||
| 80 | | 63.2 | May 2024 | Official leaderboard | |
| 81 | OpenBuddy/openbuddy-yi1.5-9b-v21.1-32k 📑 | 63.0 | Official leaderboard | ||
| 82 | byroneverson/Yi-1.5-9B-Chat-abliterated 📑 | 62.9 | Official leaderboard | ||
| 83 | NLPark/Shi-Ci_v3-Robin 📑 | 62.9 | Official leaderboard | ||
| 84 | cognitivecomputations/dolphin-2.9.1-yi-1.5-9b 📑 | 62.9 | Official leaderboard | ||
| 85 | wenbopan/Faro-Yi-9B 📑 | 62.9 | Official leaderboard | ||
| 86 | qnguyen3/Master-Yi-9B 📑 | 62.6 | Official leaderboard | ||
| 87 | Qwen/Qwen1.5-32B-Chat 📑 | 62.6 | Official leaderboard | ||
| 88 | 01-ai/Yi-1.5-9B-Chat-16K 📑 | 62.5 | Official leaderboard | ||
| 89 | cognitivecomputations/dolphin-2.9.2-mixtral-8x22b 📑 | 62.4 | Official leaderboard | ||
| 90 | duoqi/Nanbeige2-16B-Chat 📑 | 62.4 | Official leaderboard | ||
| 91 | 01-ai/Yi-1.5-9B-32K 📑 | 61.9 | Official leaderboard | ||
| 92 | 01-ai/Yi-1.5-9B 📑 | 61.8 | Official leaderboard | ||
| 93 | | 61.8 | Jun 2024 | Official leaderboard | |
| 94 | | 61.6 | Feb 2024 | Official leaderboard | |
| 95 | chujiezheng/internlm2-chat-20b-ExPO 📑 | 61.3 | Official leaderboard | ||
| 96 | migtissera/Tess-2.0-Llama-3-70B-v0.2 📑 | 61.2 | Official leaderboard | ||
| 97 | failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5 📑 | 60.9 | Official leaderboard | ||
| 98 | migtissera/Tess-M-v1.3 📑 | 60.9 | Official leaderboard | ||
| 99 | ValiantLabs/Llama3-70B-Fireplace 📑 | 60.8 | Official leaderboard | ||
| 100 | BAAI/Infinity-Instruct-7M-0729-Llama3_1-8B 📑 | 60.6 | Official leaderboard | ||
| 101 | byroneverson/Mistral-Small-Instruct-2409-abliterated 📑 | 60.5 | Official leaderboard | ||
| 102 | internlm/internlm2-chat-7b 📑 | 60.5 | Official leaderboard | ||
| 103 | Duxiaoman-DI/XuanYuan-70B-Chat 📑 | 60.5 | Official leaderboard | ||
| 104 | internlm/internlm2-chat-20b 📑 | 60.2 | Official leaderboard | ||
| 105 | xiangxinai/Xiangxin-2XL-Chat-1048k-Chinese-Llama3-70B 📑 | 60.2 | Official leaderboard | ||
| 106 | Nous-Hermes-2-Mixtral-8x7B-DPO | 60.2 | Jan 2024 | Official leaderboard | |
| 107 | sophosympatheia/Midnight-Miqu-70B-v1.5 📑 | 60.1 | Official leaderboard | ||
| 108 | GritLM/GritLM-8x7B-KTO 📑 | 60.1 | Official leaderboard | ||
| 109 | BAAI/Infinity-Instruct-3M-0625-Llama3-8B 📑 | 59.8 | Official leaderboard | ||
| 110 | internlm/internlm2-7b 📑 | 59.8 | Official leaderboard | ||
| 111 | Langboat/Mengzi3-8B-Chat 📑 | 59.7 | Official leaderboard | ||
| 112 | chujiezheng/LLaMA3-iterative-DPO-final-ExPO 📑 | 59.7 | Official leaderboard | ||
| 113 | CofeAI/Tele-FLM 📑 | 59.6 | Official leaderboard | ||
| 114 | internlm/internlm2-base-20b 📑 | 59.6 | Official leaderboard | ||
| 115 | 01-ai/Yi-34B-Chat 📑 | 59.4 | Official leaderboard | ||
| 116 | cognitivecomputations/dolphin-2.9.2-Phi-3-Medium 📑 | 59.3 | Official leaderboard | ||
| 117 | vicgalle/CarbonBeagle-11B-truthy 📑 | 59.2 | Official leaderboard | ||
| 118 | abhishek/autotrain-llama3-70b-orpo-v1 📑 | 59.1 | Official leaderboard | ||
| 119 | shenzhi-wang/Llama3-8B-Chinese-Chat 📑 | 59.0 | Official leaderboard | ||
| 120 | NotAiLOL/Yi-1.5-dolphin-9B 📑 | 58.9 | Official leaderboard | ||
| 121 | vicgalle/CarbonBeagle-11B 📑 | 58.7 | Official leaderboard | ||
| 122 | DeepMount00/Llama-3-8b-Ita 📑 | 58.7 | Official leaderboard | ||
| 123 | VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct 📑 | 58.7 | Official leaderboard | ||
| 124 | MaziyarPanahi/Llama-3-8B-Instruct-v0.8 📑 | 58.6 | Official leaderboard | ||
| 125 | Kukedlc/NeuralLLaMa-3-8b-DT-v0.1 📑 | 58.6 | Official leaderboard | ||
| 126 | GritLM/GritLM-8x7B 📑 | 58.5 | Official leaderboard | ||
| 127 | mlabonne/Daredevil-8B-abliterated 📑 | 58.5 | Official leaderboard | ||
| 128 | jondurbin/airoboros-70b-3.3 📑 | 58.5 | Official leaderboard | ||
| 129 | yaojialzc/Gigi-Llama3-8B-Chinese-zh 📑 | 58.4 | Official leaderboard | ||
| 130 | BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B 📑 | 58.4 | Official leaderboard | ||
| 131 | jondurbin/airoboros-dpo-70b-3.3 📑 | 58.4 | Official leaderboard | ||
| 132 | turboderp/Cat-Llama-3-70B-instruct 📑 | 58.4 | Official leaderboard | ||
| 133 | Yi-9B | 58.3 | Mar 2024 | Official leaderboard | |
| 134 | MaziyarPanahi/Llama-3-8B-Instruct-v0.10 📑 | 58.3 | Official leaderboard | ||
| 135 | cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated 📑 | 58.3 | Official leaderboard | ||
| 136 | mlabonne/NeuralDaredevil-8B-abliterated 📑 | 58.3 | Official leaderboard | ||
| 137 | haoranxu/Llama-3-Instruct-8B-SimPO 📑 | 58.1 | Official leaderboard | ||
| 138 | 01-ai/Yi-9B-200K 📑 | 58.1 | Official leaderboard | ||
| 139 | grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge 📑 | 58.0 | Official leaderboard | ||
| 140 | OpenBuddy/openbuddy-llama3-8b-v21.2-32k 📑 | 58.0 | Official leaderboard | ||
| 141 | vicgalle/ConfigurableBeagle-11B 📑 | 58.0 | Official leaderboard | ||
| 142 | Danielbrdz/Barcenas-Llama3-8b-ORPO 📑 | 58.0 | Official leaderboard | ||
| 143 | MaziyarPanahi/Llama-3-8B-Instruct-v0.9 📑 | 58.0 | Official leaderboard | ||
| 144 | UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 📑 | 57.9 | Official leaderboard | ||
| 145 | 01-ai/Yi-34B-200K 📑 | 57.9 | Official leaderboard | ||
| 146 | Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 📑 | 57.9 | Official leaderboard | ||
| 147 | UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2 📑 | 57.8 | Official leaderboard | ||
| 148 | mixtao/MixTAO-7Bx2-MoE-v8.1 📑 | 57.7 | Official leaderboard | ||
| 149 | shadowml/BeagSake-7B 📑 | 57.7 | Official leaderboard | ||
| 150 | shadowml/Mixolar-4x7b 📑 | 57.7 | Official leaderboard | ||
| 151 | jeonsworld/CarbonVillain-en-10.7B-v4 📑 | 57.6 | Official leaderboard | ||
| 152 | kekmodel/StopCarbon-10.7B-v5 📑 | 57.6 | Official leaderboard | ||
| 153 | hfl/chinese-mixtral-instruct 📑 | 57.6 | Official leaderboard | ||
| 154 | haoranxu/Llama-3-Instruct-8B-CPO-SimPO 📑 | 57.5 | Official leaderboard | ||
| 155 | NLPark/Test1_SLIDE 📑 | 57.5 | Official leaderboard | ||
| 156 | hfl/llama-3-chinese-8b-instruct-v2 📑 | 57.4 | Official leaderboard | ||
| 157 | invalid-coder/Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp 📑 | 57.4 | Official leaderboard | ||
| 158 | zhengr/MixTAO-7Bx2-MoE-v8.1 📑 | 57.3 | Official leaderboard | ||
| 159 | dzakwan/dzakwan-MoE-4x7b-Beta 📑 | 57.3 | Official leaderboard | ||
| 160 | RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2 📑 | 57.3 | Official leaderboard | ||
| 161 | hfl/llama-3-chinese-8b-instruct-v3 📑 | 57.3 | Official leaderboard | ||
| 162 | Magpie-Align/Llama-3-8B-Magpie-Align-v0.3 📑 | 57.2 | Official leaderboard | ||
| 163 | ghost-x/ghost-8b-beta-1608 📑 | 57.2 | Official leaderboard | ||
| 164 | | 57.2 | Dec 2023 | Official leaderboard | |
| 165 | chujiezheng/Llama3-8B-Chinese-Chat-ExPO 📑 | 57.2 | Official leaderboard | ||
| 166 | uygarkurt/llama-3-merged-linear 📑 | 57.2 | Official leaderboard | ||
| 167 | jondurbin/bagel-8b-v1.0 📑 | 57.0 | Official leaderboard | ||
| 168 | jsfs11/MixtureofMerges-MoE-4x7b-v5 📑 | 57.0 | Official leaderboard | ||
| 169 | mlabonne/ChimeraLlama-3-8B-v3 📑 | 57.0 | Official leaderboard | ||
| 170 | | 57.0 | Nov 2023 | Official leaderboard | |
| 171 | Kukedlc/NeuralSynthesis-7B-v0.3 📑 | 57.0 | Official leaderboard | ||
| 172 | mlabonne/AlphaMonarch-7B 📑 | 56.9 | Official leaderboard | ||
| 173 | mlabonne/ChimeraLlama-3-8B-v2 📑 | 56.9 | Official leaderboard | ||
| 174 | Kquant03/CognitiveFusion2-4x7B-BF16 📑 | 56.9 | Official leaderboard | ||
| 175 | meraGPT/mera-mix-4x7B 📑 | 56.8 | Official leaderboard | ||
| 176 | ibivibiv/multimaster-7b-v6 📑 | 56.8 | Official leaderboard | ||
| 177 | vicgalle/Configurable-Llama-3-8B-v0.3 📑 | 56.8 | Official leaderboard | ||
| 178 | Kukedlc/NeuralSynthesis-7B-v0.1 📑 | 56.7 | Official leaderboard | ||
| 179 | yunconglong/DARE_TIES_13B 📑 | 56.7 | Official leaderboard | ||
| 180 | mlabonne/NeuralMonarch-7B 📑 | 56.7 | Official leaderboard | ||
| 181 | yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 📑 | 56.7 | Official leaderboard | ||
| 182 | yunconglong/MoE_13B_DPO 📑 | 56.7 | Official leaderboard | ||
| 183 | Kukedlc/NeuralSynthesis-7b-v0.4-slerp 📑 | 56.7 | Official leaderboard | ||
| 184 | cognitivecomputations/WestLake-7B-v2-laser 📑 | 56.7 | Official leaderboard | ||
| 185 | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half 📑 | 56.7 | Official leaderboard | ||
| 186 | MaziyarPanahi/Calme-4x7B-MoE-v0.1 📑 | 56.6 | Official leaderboard | ||
| 187 | grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge 📑 | 56.6 | Official leaderboard | ||
| 188 | allknowingroger/MultiverseEx26-7B-slerp 📑 | 56.6 | Official leaderboard | ||
| 189 | vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B 📑 | 56.6 | Official leaderboard | ||
| 190 | jsfs11/MixtureofMerges-MoE-4x7b-v4 📑 | 56.6 | Official leaderboard | ||
| 191 | Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3 📑 | 56.6 | Official leaderboard | ||
| 192 | automerger/YamshadowExperiment28-7B 📑 | 56.6 | Official leaderboard | ||
| 193 | | 56.6 | Feb 2024 | Official leaderboard | |
| 194 | NousResearch/Hermes-2-Theta-Llama-3-8B 📑 has been flagged! See discussion #510 | 56.6 | Official leaderboard | ||
| 195 | MaziyarPanahi/Calme-4x7B-MoE-v0.2 📑 | 56.5 | Official leaderboard | ||
| 196 | | 56.4 | May 2024 | Official leaderboard | |
| 197 | CultriX/NeuralMona_MoE-4x7B 📑 | 56.4 | Official leaderboard | ||
| 198 | hfl/llama-3-chinese-8b-instruct 📑 | 56.3 | Official leaderboard | ||
| 199 | winninghealth/WiNGPT2-Llama-3-8B-Chat 📑 | 56.3 | Official leaderboard | ||
| 200 | ibivibiv/llama-3-nectar-dpo-8B 📑 | 56.3 | Official leaderboard | ||
| 201 | mlabonne/Beyonder-4x7B-v3 📑 | 56.3 | Official leaderboard | ||
| 202 | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25 📑 | 56.3 | Official leaderboard | ||
| 203 | chujiezheng/internlm2-chat-7b-ExPO 📑 | 56.2 | Official leaderboard | ||
| 204 | Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4 📑 | 56.2 | Official leaderboard | ||
| 205 | failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 📑 | 56.1 | Official leaderboard | ||
| 206 | 01-ai/Yi-1.5-6B 📑 | 56.0 | Official leaderboard | ||
| 207 | lightblue/suzume-llama-3-8B-multilingual 📑 | 56.0 | Official leaderboard | ||
| 208 | Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5 📑 | 56.0 | Official leaderboard | ||
| 209 | MaziyarPanahi/Topxtral-4x7B-v0.1 📑 | 55.9 | Official leaderboard | ||
| 210 | chujiezheng/tulu-2-dpo-70b-ExPO 📑 | 55.9 | Official leaderboard | ||
| 211 | abacusai/Smaug-Mixtral-v0.1 📑 | 55.8 | Official leaderboard | ||
| 212 | princeton-nlp/Llama-3-8B-ProLong-512k-Instruct 📑 | 55.8 | Official leaderboard | ||
| 213 | vaiv/GeM2-Llamion-14B-Base 📑 | 55.7 | Official leaderboard | ||
| 214 | OpenBuddy/openbuddy-zero-14b-v22.3-32k 📑 | 55.6 | Official leaderboard | ||
| 215 | openchat/openchat-3.6-8b-20240522 📑 | 55.6 | Official leaderboard | ||
| 216 | eldogbbhed/Peagle-9b 📑 | 55.5 | Official leaderboard | ||
| 217 | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75 📑 | 55.4 | Official leaderboard | ||
| 218 | abacusai/Slerp-CM-mist-dpo 📑 | 55.3 | Official leaderboard | ||
| 219 | migtissera/Llama-3-8B-Synthia-v3.5 📑 | 55.2 | Official leaderboard | ||
| 220 | failspy/Codestral-22B-v0.1-abliterated-v3 📑 | 55.1 | Official leaderboard | ||
| 221 | NousResearch/Meta-Llama-3-8B-Instruct 📑 | 55.1 | Official leaderboard | ||
| 222 | duoqi/Nanbeige-16B-Base-Llama 📑 | 55.0 | Official leaderboard | ||
| 223 | princeton-nlp/Llama-3-8B-ProLong-64k-Instruct 📑 | 54.9 | Official leaderboard | ||
| 224 | Qwen/Qwen1.5-MoE-A2.7B 📑 | 54.8 | Official leaderboard | ||
| 225 | NousResearch/Nous-Hermes-2-SOLAR-10.7B 📑 | 54.8 | Official leaderboard | ||
| 226 | HIT-SCIR/Chinese-Mixtral-8x7B 📑 | 54.7 | Official leaderboard | ||
| 227 | hfl/chinese-mixtral 📑 | 54.6 | Official leaderboard | ||
| 228 | princeton-nlp/Llama-3-8B-ProLong-64k-Base 📑 | 54.6 | Official leaderboard | ||
| 229 | lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full 📑 | 54.6 | Official leaderboard | ||
| 230 | rombodawg/rombos_Replete-Coder-Instruct-8b-Merged 📑 | 54.5 | Official leaderboard | ||
| 231 | liminerity/M7-7b 📑 | 54.5 | Official leaderboard | ||
| 232 | deepseek-ai/deepseek-llm-7b-chat 📑 | 54.3 | Official leaderboard | ||
| 233 | princeton-nlp/Llama-3-8B-ProLong-512k-Base 📑 | 54.1 | Official leaderboard | ||
| 234 | Weyaxi/Einstein-v6.1-Llama3-8B 📑 | 54.1 | Official leaderboard | ||
| 235 | cognitivecomputations/openchat-3.5-0106-laser 📑 | 53.8 | Official leaderboard | ||
| 236 | openchat/openchat-3.5-0106 📑 | 53.7 | Official leaderboard | ||
| 237 | chujiezheng/Starling-LM-7B-beta-ExPO 📑 | 53.7 | Official leaderboard | ||
| 238 | freewheelin/free-solar-evo-v0.13 📑 | 53.7 | Official leaderboard | ||
| 239 | abacusai/Llama-3-Smaug-8B 📑 | 53.7 | Official leaderboard | ||
| 240 | cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2 📑 | 53.6 | Official leaderboard | ||
| 241 | | 53.6 | May 2024 | Official leaderboard | |
| 242 | freewheelin/free-solar-evo-v0.11 📑 | 53.5 | Official leaderboard | ||
| 243 | Artples/L-MChat-7b 📑 | 53.3 | Official leaderboard | ||
| 244 | vaiv/GeM2-Llamion-14B-Chat 📑 | 53.3 | Official leaderboard | ||
| 245 | abacusai/bigyi-15b 📑 | 53.2 | Official leaderboard | ||
| 246 | vicgalle/ConfigurableHermes-7B 📑 | 53.1 | Official leaderboard | ||
| 247 | freewheelin/free-solar-evo-v0.1 📑 | 53.0 | Official leaderboard | ||
| 248 | | 53.0 | Nov 2023 | Official leaderboard | |
| 249 | Qwen/Qwen1.5-MoE-A2.7B-Chat 📑 | 52.8 | Official leaderboard | ||
| 250 | MoaData/Myrrh_solar_10.7b_3.0 📑 | 52.7 | Official leaderboard | ||
| 251 | winninghealth/WiNGPT2-Llama-3-8B-Base 📑 | 52.7 | Official leaderboard | ||
| 252 | FlagAlpha/Llama3-Chinese-8B-Instruct 📑 | 52.6 | Official leaderboard | ||
| 253 | migtissera/Tess-2.0-Llama-3-8B 📑 | 52.5 | Official leaderboard | ||
| 254 | shanchen/llama3-8B-slerp-med-chinese 📑 | 52.4 | Official leaderboard | ||
| 255 | MTSAIR/multi_verse_model 📑 | 52.3 | Official leaderboard | ||
| 256 | SeaLLMs/SeaLLM-7B-v2 📑 | 52.3 | Official leaderboard | ||
| 257 | tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1 📑 | 51.9 | Official leaderboard | ||
| 258 | UnicomLLM/Unichat-llama3-Chinese-8B 📑 | 51.6 | Official leaderboard | ||
| 259 | | 51.5 | Jun 2024 | Official leaderboard | |
| 260 | vaiv/GeM2-Llamion-14B-LongChat 📑 | 51.5 | Official leaderboard | ||
| 261 | | 51.4 | Feb 2024 | Official leaderboard | |
| 262 | freewheelin/free-llama3-dpo-v0.2 📑 | 51.4 | Official leaderboard | ||
| 263 | rombodawg/Everyone-Coder-4x7b-Base 📑 | 51.3 | Official leaderboard | ||
| 264 | chujiezheng/Starling-LM-7B-alpha-ExPO 📑 | 51.3 | Official leaderboard | ||
| 265 | refuelai/Llama-3-Refueled 📑 | 51.2 | Official leaderboard | ||
| 266 | speakleash/Bielik-11B-v2.3-Instruct 📑 | 50.9 | Official leaderboard | ||
| 267 | upstage/SOLAR-10.7B-v1.0 📑 | 50.9 | Official leaderboard | ||
| 268 | vicgalle/Configurable-Janus-7B 📑 | 50.9 | Official leaderboard | ||
| 269 | Qwen/Qwen1.5-4B 📑 | 50.8 | Official leaderboard | ||
| 270 | UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 📑 | 50.7 | Official leaderboard | ||
| 271 | internlm/internlm2-base-7b 📑 | 50.4 | Official leaderboard | ||
| 272 | GritLM/GritLM-7B-KTO 📑 | 50.4 | Official leaderboard | ||
| 273 | UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3 📑 | 50.3 | Official leaderboard | ||
| 274 | kaist-ai/janus-dpo-7b 📑 | 50.2 | Official leaderboard | ||
| 275 | scb10x/llama-3-typhoon-v1.5-8b-instruct 📑 | 50.1 | Official leaderboard | ||
| 276 | | 50.1 | Apr 2024 | Official leaderboard | |
| 277 | rombodawg/rombos_Replete-Coder-Llama3-8B 📑 | 50.0 | Official leaderboard | ||
| 278 | beowolx/CodeNinja-1.0-OpenChat-7B 📑 | 50.0 | Official leaderboard | ||
| 279 | dfurman/Llama-3-8B-Orpo-v0.1 📑 | 49.9 | Official leaderboard | ||
| 280 | kaist-ai/mistral-orpo-capybara-7k 📑 | 49.8 | Official leaderboard | ||
| 281 | cognitivecomputations/dolphin-2.9.1-llama-3-8b 📑 | 49.6 | Official leaderboard | ||
| 282 | kaist-ai/janus-7b 📑 | 49.5 | Official leaderboard | ||
| 283 | ChatGLM3-6B | 49.4 | Oct 2023 | Official leaderboard | |
| 284 | nvidia/Llama3-ChatQA-1.5-8B 📑 | 49.4 | Official leaderboard | ||
| 285 | openbmb/MiniCPM-2B-sft-bf16 📑 | 49.4 | Official leaderboard | ||
| 286 | hfl/chinese-alpaca-2-13b 📑 | 49.3 | Official leaderboard | ||
| 287 | | 49.2 | Jun 2024 | Official leaderboard | |
| 288 | AIJUUD/juud-Mistral-7B-dpo 📑 | 49.1 | Official leaderboard | ||
| 289 | | 49.0 | Dec 2023 | Official leaderboard | |
| 290 | | 49.0 | Apr 2024 | Official leaderboard | |
| 291 | uukuguy/speechless-zephyr-code-functionary-7b 📑 | 48.9 | Official leaderboard | ||
| 292 | 01-ai/Yi-Coder-9B-Chat 📑 | 48.9 | Official leaderboard | ||
| 293 | uukuguy/speechless-code-mistral-7b-v1.0 📑 | 48.9 | Official leaderboard | ||
| 294 | abacusai/bigstral-12b-32k 📑 | 48.8 | Official leaderboard | ||
| 295 | chujiezheng/Mistral7B-PairRM-SPPO-ExPO 📑 | 48.6 | Official leaderboard | ||
| 296 | shanchen/llama3-8B-slerp-biomed-chat-chinese 📑 | 48.5 | Official leaderboard | ||
| 297 | 01-ai/Yi-Coder-9B 📑 | 48.4 | Official leaderboard | ||
| 298 | vicgalle/Configurable-Mistral-7B 📑 | 47.8 | Official leaderboard | ||
| 299 | oobabooga/CodeBooga-34B-v0.1 📑 | 47.5 | Official leaderboard | ||
| 300 | kaist-ai/janus-orpo-7b 📑 | 47.5 | Official leaderboard | ||
| 301 | | 47.5 | Sep 2023 | Official leaderboard | |
| 302 | royallab/ZephRP-m7b 📑 | 47.3 | Official leaderboard | ||
| 303 | maywell/Synatra-7B-v0.3-RP 📑 | 46.6 | Official leaderboard | ||
| 304 | hfl/chinese-alpaca-2-13b-16k 📑 | 46.5 | Official leaderboard | ||
| 305 | cognitivecomputations/dolphin-2.6-mixtral-8x7b 📑 | 45.7 | Official leaderboard | ||
| 306 | deepseek-ai/deepseek-llm-7b-base 📑 | 45.2 | Official leaderboard | ||
| 307 | aws-prototyping/MegaBeam-Mistral-7B-512k 📑 | 45.2 | Official leaderboard | ||
| 308 | amazon/MegaBeam-Mistral-7B-300k 📑 | 44.7 | Official leaderboard | ||
| 309 | SenseLLM/ReflectionCoder-DS-33B 📑 | 44.6 | Official leaderboard | ||
| 310 | Azure99/blossom-v5.1-9b 📑 | 44.5 | Official leaderboard | ||
| 311 | hfl/chinese-llama-2-13b 📑 | 43.8 | Official leaderboard | ||
| 312 | Qwen/Qwen1.5-1.8B-Chat 📑 | 43.6 | Official leaderboard | ||
| 313 | SenseLLM/ReflectionCoder-CL-34B 📑 | 43.1 | Official leaderboard | ||
| 314 | Infinirc/Infinirc-Llama3-8B-2G-Release-v1.0 📑 | 42.9 | Official leaderboard | ||
| 315 | UnicomLLM/Unichat-llama3-Chinese-8B-28K 📑 | 42.5 | Official leaderboard | ||
| 316 | hfl/chinese-llama-2-13b-16k 📑 | 42.4 | Official leaderboard | ||
| 317 | haoranxu/ALMA-13B-Pretrain 📑 | 41.7 | Official leaderboard | ||
| 318 | Qwen/Qwen1.5-1.8B 📑 | 41.7 | Official leaderboard | ||
| 319 | scb10x/llama-3-typhoon-v1.5-8b 📑 | 41.3 | Official leaderboard | ||
| 320 | haoranxu/ALMA-13B-R 📑 | 40.6 | Official leaderboard | ||
| 321 | | 40.0 | Jun 2024 | Official leaderboard | |
| 322 | deepseek-ai/deepseek-coder-6.7b-instruct 📑 | 39.9 | Official leaderboard | ||
| 323 | OpenBuddy/openbuddy-mistral-22b-v21.1-32k 📑 | 39.6 | Official leaderboard | ||
| 324 | | 38.6 | Jun 2024 | Official leaderboard | |
| 325 | SeaLLMs/SeaLLM-7B-v2.5 📑 | 38.5 | Official leaderboard | ||
| 326 | Qwen/Qwen1.5-0.5B-Chat 📑 | 36.7 | Official leaderboard | ||
| 327 | haoranxu/ALMA-7B-R 📑 | 36.4 | Official leaderboard | ||
| 328 | Qwen/Qwen1.5-0.5B 📑 | 35.8 | Official leaderboard | ||
| 329 | cognitivecomputations/dolphin-2.9.1-mixtral-1x22b 📑 | 35.0 | Official leaderboard | ||
| 330 | RLHFlow/ArmoRM-Llama3-8B-v0.1 📑 | 34.4 | Official leaderboard | ||
| 331 | | 34.3 | Apr 2024 | Official leaderboard | |
| 332 | | 33.8 | Feb 2024 | Official leaderboard | |
| 333 | | 33.4 | Feb 2024 | Official leaderboard | |
| 334 | | 33.1 | Dec 2023 | Official leaderboard | |
| 335 | Artples/L-MChat-Small 📑 | 32.4 | Official leaderboard | ||
| 336 | | 30.7 | Sep 2023 | Official leaderboard | |
| 337 | deepseek-ai/deepseek-coder-1.3b-instruct 📑 | 30.2 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 75.7 | Jun 2024 | Official leaderboard | |
| 2 | | 70.5 | Feb 2024 | Official leaderboard | |
| 3 | | 66.7 | May 2024 | Official leaderboard | |
| 4 | | 66.6 | Feb 2024 | Official leaderboard | |
| 5 | | 66.0 | Feb 2024 | Official leaderboard | |
| 6 | | 65.3 | Nov 2023 | Official leaderboard | |
| 7 | | 64.3 | May 2024 | Official leaderboard | |
| 8 | | 64.2 | Apr 2024 | Official leaderboard | |
| 9 | | 63.5 | Jun 2024 | Official leaderboard | |
| 10 | | 63.2 | May 2024 | Official leaderboard | |
| 11 | | 61.8 | Jun 2024 | Official leaderboard | |
| 12 | | 61.6 | Feb 2024 | Official leaderboard | |
| 13 | Nous-Hermes-2-Mixtral-8x7B-DPO | 60.2 | Jan 2024 | Official leaderboard | |
| 14 | Yi-9B | 58.3 | Mar 2024 | Official leaderboard | |
| 15 | | 57.2 | Dec 2023 | Official leaderboard | |
| 16 | | 57.0 | Nov 2023 | Official leaderboard | |
| 17 | | 56.6 | Feb 2024 | Official leaderboard | |
| 18 | | 56.4 | May 2024 | Official leaderboard | |
| 19 | | 53.6 | May 2024 | Official leaderboard | |
| 20 | | 53.0 | Nov 2023 | Official leaderboard | |
| 21 | | 51.5 | Jun 2024 | Official leaderboard | |
| 22 | | 51.4 | Feb 2024 | Official leaderboard | |
| 23 | | 50.1 | Apr 2024 | Official leaderboard | |
| 24 | ChatGLM3-6B | 49.4 | Oct 2023 | Official leaderboard | |
| 25 | | 49.2 | Jun 2024 | Official leaderboard | |
| 26 | | 49.0 | Dec 2023 | Official leaderboard | |
| 27 | | 49.0 | Apr 2024 | Official leaderboard | |
| 28 | | 47.5 | Sep 2023 | Official leaderboard | |
| 29 | | 40.0 | Jun 2024 | Official leaderboard | |
| 30 | | 38.6 | Jun 2024 | Official leaderboard | |
| 31 | | 34.3 | Apr 2024 | Official leaderboard | |
| 32 | | 33.8 | Feb 2024 | Official leaderboard | |
| 33 | | 33.4 | Feb 2024 | Official leaderboard | |
| 34 | | 33.1 | Dec 2023 | Official leaderboard | |
| 35 | | 30.7 | Sep 2023 | Official leaderboard |
2 models have held number one on the official leaderboard since its release in May 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Open Chinese LLM Leaderboard leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Open Chinese LLM Leaderboard 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in June 2024, for Qwen2-0.5B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (337 entries).
- Pass Models scored 35 models we track, plus 302 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in June 2024, for Qwen2-0.5B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen2-72B (#180).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 37 rows for models we track and 302 other entries at the last read.
- Pass Last read November 21st, 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.