LLMzSzŁ
Models answer Polish academic and professional exam questions drawn from the Central Examination Board archives.
The authors compare models on four kinds of exams spanning 154 domains.
- Made by
- Krzysztof Jassem and colleagues
- Released
- January 2025
- Kind
- Knowledge in many languages
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Mathematics, Languages and literature, Other engineering and technologies, Economics and business, Biological sciences
- Language
- Polish
- Interaction
- Single turn
- Items from
- Exams and contests
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Biology and medicine, Law and finance
- Strongest model tested
-
Qwen3-32B #135 on the capability index
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
Qwen2.5-72B leads with 69.1% among models released by April 2025 Qwen2.5-72B leads with 69.1% among models released by April 2025
Best score per entry from the benchmark's own 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. This view shows only models we track, each at its best.
The newest model with a score here came out in April 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
- 69.1
Qwen2.5-72B
- 67.2 mistralai/Mistral-Large-Instruct-2407
- 67.1
Llama 3.3 70B Instruct
- 66.8
Qwen3-32B
- 66.6 mistralai/Mistral-Large-Instruct-2411
- 66.6 meta-llama/Meta-Llama-3.1-70B-Instruct
- 64.6 CYFRAGOVPL/Llama-PLLuM-70B-base
- 64.4 CYFRAGOVPL/Llama-PLLuM-70B-chat
- 64.0 meta-llama/Meta-Llama-3-70B-Instruct
- 63.5
Qwen3-30B-A3B
- 63.1
Llama 3.1-70B
- 62.2
Llama 3-70B
- 61.0
Qwen2.5-32B
- 61.0
Qwen3-14B
- 60.5 CYFRAGOVPL/PLLuM-8x7B-nc-chat
- 59.2 speakleash/Bielik-11B-v2.6-Instruct
- 58.9 speakleash/Bielik-11B-v2.5-Instruct
- 58.2 mistralai/Mixtral-8x22B-Instruct-v0.1
- 57.8 CYFRAGOVPL/PLLuM-8x7B-nc-base
- 57.5 speakleash/Bielik-11B-v2.1-Instruct
- 57.4 speakleash/Bielik-11B-v2.3-Instruct
- 57.4 speakleash/Bielik-11B-v2.2-Instruct
- 55.8
DeepSeek-R1-Distill-Qwen-32B
- 55.6 speakleash/Bielik-11B-v2.0-Instruct
- 55.3
Qwen2.5-14B
- 55.3
Qwen3-8B
- 55.1 speakleash/Bielik-11B-v2
- 54.8 speakleash/Bielik-4.5B-v3.0-Instruct
- 54.2 CYFRAGOVPL/PLLuM-12b-nc-chat-250715
- 53.4 CYFRAGOVPL/PLLuM-12B-nc-chat
- 52.8 CYFRAGOVPL/PLLuM-8x7B-chat
- 52.2 CYFRAGOVPL/PLLuM-8x7B-base
- 51.8
Phi-4
- 51.4 utter-project/EuroLLM-9B-Instruct
- 50.5 CYFRAGOVPL/PLLuM-12B-nc-base
- 50.2
Qwen3-4B
- 49.7 CYFRAGOVPL/PLLuM-12B-chat
- 49.5 mistralai/Mixtral-8x7B-Instruct-v0.1
- 47.7
Mixtral 8x7B
- 47.7 CYFRAGOVPL/Llama-PLLuM-8B-chat
- 47.4 meta-llama/Meta-Llama-3.1-8B-Instruct
- 46.8
Gemma 7B
- 46.8 speakleash/Bielik-1.5B-v3.0-Instruct
- 46.8
DeepSeek-R1-Distill-Qwen-14B
- 46.5 CYFRAGOVPL/PLLuM-12B-base
- 46.4 meta-llama/Llama-2-70b-hf
- 46.3 CYFRAGOVPL/Llama-PLLuM-8B-base
- 45.6
Qwen2-7B
- 45.5 mistralai/Mistral-Nemo-Instruct-2407
- 44.8 meta-llama/Meta-Llama-3-8B-Instruct
- 44.2
Llama 3.1-8B
- 44.2
OLMo 2 32B Instruct
- 42.3 mistralai/Ministral-8B-Instruct-2410
- 42.2
Mistral-Nemo-Base-2407
- 41.8 allenai/OLMo-2-0325-32B
- 41.7 mistralai/Mistral-7B-Instruct-v0.3
- 41.5 01-ai/Yi-1.5-34B-Chat
- 41.4 01-ai/Yi-34B-Chat
- 41.4
Llama 3-8B
- 41.1
Yi-1.5-34B
- 40.8 speakleash/Bielik-7B-Instruct-v0.1
- 40.8
Mistral-7B-Instruct-v0.2
- 40.3 01-ai/Yi-34B-Chat-4bits
- 40.2 Voicelab/trurl-2-13b-8bit
- 40.2 Voicelab/trurl-2-13b
- 39.9
Qwen3-1.7B
- 39.9 meta-llama/Llama-3.2-3B-Instruct
- 39.1 speakleash/Bielik-7B-v0.1
- 38.2 lucyknada/microsoft_WizardLM-2-7B
- 37.8
Mistral 7B v0.1
- 37.6
Yi-1.5-9B-Chat
- 37.6 01-ai/Yi-34B-200K
- 37.1
Mistral 7B v0.3
- 37.1 01-ai/Yi-1.5-9B
- 36.0
Mistral-7B-Instruct-v0.1
- 34.9 Voicelab/trurl-2-13b-academic
- 34.9 OPI-PG/Qra-13b
- 34.2
Qwen2-1.5B
- 33.9 meta-llama/Llama-2-13b-hf
- 33.4
phi-3-mini 3.8B
- 33.2 allenai/OLMo-2-1124-13B-Instruct
- 32.6 allenai/OLMo-2-1124-13B
- 32.3 Voicelab/trurl-2-7b
- 31.9 Voicelab/trurl-2-7b-8bit
- 31.6 meta-llama/Llama-3.2-1B-Instruct
- 31.5 allenai/OLMo-2-1124-7B-Instruct
- 31.1 allenai/OLMo-2-1124-7B
- 29.1 OPI-PG/Qra-7b
- 28.0 meta-llama/Llama-2-7b-hf
- 25.7 microsoft/phi-1
- 25.6 utter-project/EuroLLM-1.7B-Instruct
- 25.6
Phi-2
- 25.5 OPI-PG/Qra-1b
- 24.9 sdadas/polish-gpt2-large
- 24.4 sdadas/polish-gpt2-medium
- 24.3
Phi-1.5
- 24.2 sdadas/polish-gpt2-small
- 24.0 sdadas/polish-gpt2-xl
- 1
Qwen2.5-72B 69.1%
- 2 mistralai/Mistral-Large-Instruct-2407 67.2%
- 3
Llama 3.3 70B Instruct 67.1%
- 4
Qwen3-32B 66.8%
- 5 mistralai/Mistral-Large-Instruct-2411 66.6%
- 6 meta-llama/Meta-Llama-3.1-70B-Instruct 66.6%
- 7 CYFRAGOVPL/Llama-PLLuM-70B-base 64.6%
- 8 CYFRAGOVPL/Llama-PLLuM-70B-chat 64.4%
- 9 meta-llama/Meta-Llama-3-70B-Instruct 64%
- 10
Qwen3-30B-A3B 63.5%
- 11
Llama 3.1-70B 63.1%
- 12
Llama 3-70B 62.2%
- 13
Qwen2.5-32B 61%
- 14
Qwen3-14B 61%
- 15 CYFRAGOVPL/PLLuM-8x7B-nc-chat 60.5%
- 16 speakleash/Bielik-11B-v2.6-Instruct 59.2%
- 17 speakleash/Bielik-11B-v2.5-Instruct 58.9%
- 18 mistralai/Mixtral-8x22B-Instruct-v0.1 58.2%
- 19 CYFRAGOVPL/PLLuM-8x7B-nc-base 57.8%
- 20 speakleash/Bielik-11B-v2.1-Instruct 57.5%
- 21 speakleash/Bielik-11B-v2.3-Instruct 57.4%
- 22 speakleash/Bielik-11B-v2.2-Instruct 57.4%
- 23
DeepSeek-R1-Distill-Qwen-32B 55.8%
- 24 speakleash/Bielik-11B-v2.0-Instruct 55.6%
- 25
Qwen2.5-14B 55.3%
- 26
Qwen3-8B 55.3%
- 27 speakleash/Bielik-11B-v2 55.1%
- 28 speakleash/Bielik-4.5B-v3.0-Instruct 54.8%
- 29 CYFRAGOVPL/PLLuM-12b-nc-chat-250715 54.2%
- 30 CYFRAGOVPL/PLLuM-12B-nc-chat 53.4%
- 31 CYFRAGOVPL/PLLuM-8x7B-chat 52.8%
- 32 CYFRAGOVPL/PLLuM-8x7B-base 52.2%
- 33
Phi-4 51.8%
- 34 utter-project/EuroLLM-9B-Instruct 51.4%
- 35 CYFRAGOVPL/PLLuM-12B-nc-base 50.5%
- 36
Qwen3-4B 50.2%
- 37 CYFRAGOVPL/PLLuM-12B-chat 49.7%
- 38 mistralai/Mixtral-8x7B-Instruct-v0.1 49.5%
- 39
Mixtral 8x7B 47.7%
- 40 CYFRAGOVPL/Llama-PLLuM-8B-chat 47.7%
- 41 meta-llama/Meta-Llama-3.1-8B-Instruct 47.4%
- 42
Gemma 7B 46.8%
- 43 speakleash/Bielik-1.5B-v3.0-Instruct 46.8%
- 44
DeepSeek-R1-Distill-Qwen-14B 46.8%
- 45 CYFRAGOVPL/PLLuM-12B-base 46.5%
- 46 meta-llama/Llama-2-70b-hf 46.4%
- 47 CYFRAGOVPL/Llama-PLLuM-8B-base 46.3%
- 48
Qwen2-7B 45.6%
- 49 mistralai/Mistral-Nemo-Instruct-2407 45.5%
- 50 meta-llama/Meta-Llama-3-8B-Instruct 44.8%
- 51
Llama 3.1-8B 44.2%
- 52
OLMo 2 32B Instruct 44.2%
- 53 mistralai/Ministral-8B-Instruct-2410 42.3%
- 54
Mistral-Nemo-Base-2407 42.2%
- 55 allenai/OLMo-2-0325-32B 41.8%
- 56 mistralai/Mistral-7B-Instruct-v0.3 41.7%
- 57 01-ai/Yi-1.5-34B-Chat 41.5%
- 58 01-ai/Yi-34B-Chat 41.4%
- 59
Llama 3-8B 41.4%
- 60
Yi-1.5-34B 41.1%
- 61 speakleash/Bielik-7B-Instruct-v0.1 40.8%
- 62
Mistral-7B-Instruct-v0.2 40.8%
- 63 01-ai/Yi-34B-Chat-4bits 40.3%
- 64 Voicelab/trurl-2-13b-8bit 40.2%
- 65 Voicelab/trurl-2-13b 40.2%
- 66
Qwen3-1.7B 39.9%
- 67 meta-llama/Llama-3.2-3B-Instruct 39.9%
- 68 speakleash/Bielik-7B-v0.1 39.1%
- 69 lucyknada/microsoft_WizardLM-2-7B 38.2%
- 70
Mistral 7B v0.1 37.8%
- 71
Yi-1.5-9B-Chat 37.6%
- 72 01-ai/Yi-34B-200K 37.6%
- 73
Mistral 7B v0.3 37.1%
- 74 01-ai/Yi-1.5-9B 37.1%
- 75
Mistral-7B-Instruct-v0.1 36%
- 76 Voicelab/trurl-2-13b-academic 34.9%
- 77 OPI-PG/Qra-13b 34.9%
- 78
Qwen2-1.5B 34.2%
- 79 meta-llama/Llama-2-13b-hf 33.9%
- 80
phi-3-mini 3.8B 33.4%
- 81 allenai/OLMo-2-1124-13B-Instruct 33.2%
- 82 allenai/OLMo-2-1124-13B 32.6%
- 83 Voicelab/trurl-2-7b 32.3%
- 84 Voicelab/trurl-2-7b-8bit 31.9%
- 85 meta-llama/Llama-3.2-1B-Instruct 31.6%
- 86 allenai/OLMo-2-1124-7B-Instruct 31.5%
- 87 allenai/OLMo-2-1124-7B 31.1%
- 88 OPI-PG/Qra-7b 29.1%
- 89 meta-llama/Llama-2-7b-hf 28%
- 90 microsoft/phi-1 25.7%
- 91 utter-project/EuroLLM-1.7B-Instruct 25.6%
- 92
Phi-2 25.6%
- 93 OPI-PG/Qra-1b 25.5%
- 94 sdadas/polish-gpt2-large 24.9%
- 95 sdadas/polish-gpt2-medium 24.4%
- 96
Phi-1.5 24.3%
- 97 sdadas/polish-gpt2-small 24.2%
- 98 sdadas/polish-gpt2-xl 24%
Source: Official LLMzSzŁ leaderboard
- 69.1
Qwen2.5-72B
- 67.1
Llama 3.3 70B Instruct
- 66.8
Qwen3-32B
- 63.5
Qwen3-30B-A3B
- 63.1
Llama 3.1-70B
- 62.2
Llama 3-70B
- 61.0
Qwen2.5-32B
- 61.0
Qwen3-14B
- 55.8
DeepSeek-R1-Distill-Qwen-32B
- 55.3
Qwen2.5-14B
- 55.3
Qwen3-8B
- 51.8
Phi-4
- 50.2
Qwen3-4B
- 47.7
Mixtral 8x7B
- 46.8
Gemma 7B
- 46.8
DeepSeek-R1-Distill-Qwen-14B
- 45.6
Qwen2-7B
- 44.2
Llama 3.1-8B
- 44.2
OLMo 2 32B Instruct
- 42.2
Mistral-Nemo-Base-2407
- 41.4
Llama 3-8B
- 41.1
Yi-1.5-34B
- 40.8
Mistral-7B-Instruct-v0.2
- 39.9
Qwen3-1.7B
- 37.8
Mistral 7B v0.1
- 37.6
Yi-1.5-9B-Chat
- 37.1
Mistral 7B v0.3
- 36.0
Mistral-7B-Instruct-v0.1
- 34.2
Qwen2-1.5B
- 33.4
phi-3-mini 3.8B
- 25.6
Phi-2
- 24.3
Phi-1.5
- 1
Qwen2.5-72B 69.1%
- 2
Llama 3.3 70B Instruct 67.1%
- 3
Qwen3-32B 66.8%
- 4
Qwen3-30B-A3B 63.5%
- 5
Llama 3.1-70B 63.1%
- 6
Llama 3-70B 62.2%
- 7
Qwen2.5-32B 61%
- 8
Qwen3-14B 61%
- 9
DeepSeek-R1-Distill-Qwen-32B 55.8%
- 10
Qwen2.5-14B 55.3%
- 11
Qwen3-8B 55.3%
- 12
Phi-4 51.8%
- 13
Qwen3-4B 50.2%
- 14
Mixtral 8x7B 47.7%
- 15
Gemma 7B 46.8%
- 16
DeepSeek-R1-Distill-Qwen-14B 46.8%
- 17
Qwen2-7B 45.6%
- 18
Llama 3.1-8B 44.2%
- 19
OLMo 2 32B Instruct 44.2%
- 20
Mistral-Nemo-Base-2407 42.2%
- 21
Llama 3-8B 41.4%
- 22
Yi-1.5-34B 41.1%
- 23
Mistral-7B-Instruct-v0.2 40.8%
- 24
Qwen3-1.7B 39.9%
- 25
Mistral 7B v0.1 37.8%
- 26
Yi-1.5-9B-Chat 37.6%
- 27
Mistral 7B v0.3 37.1%
- 28
Mistral-7B-Instruct-v0.1 36%
- 29
Qwen2-1.5B 34.2%
- 30
phi-3-mini 3.8B 33.4%
- 31
Phi-2 25.6%
- 32
Phi-1.5 24.3%
Source: Official LLMzSzŁ leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 69.1% | Sep 2024 | Official leaderboard | |
| 2 | mistralai/Mistral-Large-Instruct-2407 | 67.2% | Official leaderboard | ||
| 3 | | 67.1% | Dec 2024 | Official leaderboard | |
| 4 | | 66.8% | Apr 2025 | Official leaderboard | |
| 5 | mistralai/Mistral-Large-Instruct-2411 | 66.6% | Official leaderboard | ||
| 6 | meta-llama/Meta-Llama-3.1-70B-Instruct | 66.6% | Official leaderboard | ||
| 7 | CYFRAGOVPL/Llama-PLLuM-70B-base | 64.6% | Official leaderboard | ||
| 8 | CYFRAGOVPL/Llama-PLLuM-70B-chat | 64.4% | Official leaderboard | ||
| 9 | meta-llama/Meta-Llama-3-70B-Instruct | 64% | Official leaderboard | ||
| 10 | | 63.5% | Apr 2025 | Official leaderboard | |
| 11 | | 63.1% | Jul 2024 | Official leaderboard | |
| 12 | | 62.2% | Apr 2024 | Official leaderboard | |
| 13 | | 61% | Sep 2024 | Official leaderboard | |
| 14 | | 61% | Apr 2025 | Official leaderboard | |
| 15 | CYFRAGOVPL/PLLuM-8x7B-nc-chat | 60.5% | Official leaderboard | ||
| 16 | speakleash/Bielik-11B-v2.6-Instruct | 59.2% | Official leaderboard | ||
| 17 | speakleash/Bielik-11B-v2.5-Instruct | 58.9% | Official leaderboard | ||
| 18 | mistralai/Mixtral-8x22B-Instruct-v0.1 | 58.2% | Official leaderboard | ||
| 19 | CYFRAGOVPL/PLLuM-8x7B-nc-base | 57.8% | Official leaderboard | ||
| 20 | speakleash/Bielik-11B-v2.1-Instruct | 57.5% | Official leaderboard | ||
| 21 | speakleash/Bielik-11B-v2.3-Instruct | 57.4% | Official leaderboard | ||
| 22 | speakleash/Bielik-11B-v2.2-Instruct | 57.4% | Official leaderboard | ||
| 23 | | 55.8% | Jan 2025 | Official leaderboard | |
| 24 | speakleash/Bielik-11B-v2.0-Instruct | 55.6% | Official leaderboard | ||
| 25 | | 55.3% | Sep 2024 | Official leaderboard | |
| 26 | | 55.3% | Apr 2025 | Official leaderboard | |
| 27 | speakleash/Bielik-11B-v2 | 55.1% | Official leaderboard | ||
| 28 | speakleash/Bielik-4.5B-v3.0-Instruct | 54.8% | Official leaderboard | ||
| 29 | CYFRAGOVPL/PLLuM-12b-nc-chat-250715 | 54.2% | Official leaderboard | ||
| 30 | CYFRAGOVPL/PLLuM-12B-nc-chat | 53.4% | Official leaderboard | ||
| 31 | CYFRAGOVPL/PLLuM-8x7B-chat | 52.8% | Official leaderboard | ||
| 32 | CYFRAGOVPL/PLLuM-8x7B-base | 52.2% | Official leaderboard | ||
| 33 | | 51.8% | Dec 2024 | Official leaderboard | |
| 34 | utter-project/EuroLLM-9B-Instruct | 51.4% | Official leaderboard | ||
| 35 | CYFRAGOVPL/PLLuM-12B-nc-base | 50.5% | Official leaderboard | ||
| 36 | | 50.2% | Apr 2025 | Official leaderboard | |
| 37 | CYFRAGOVPL/PLLuM-12B-chat | 49.7% | Official leaderboard | ||
| 38 | mistralai/Mixtral-8x7B-Instruct-v0.1 | 49.5% | Official leaderboard | ||
| 39 | | 47.7% | Dec 2023 | Official leaderboard | |
| 40 | CYFRAGOVPL/Llama-PLLuM-8B-chat | 47.7% | Official leaderboard | ||
| 41 | meta-llama/Meta-Llama-3.1-8B-Instruct | 47.4% | Official leaderboard | ||
| 42 | | 46.8% | Feb 2024 | Official leaderboard | |
| 43 | speakleash/Bielik-1.5B-v3.0-Instruct | 46.8% | Official leaderboard | ||
| 44 | | 46.8% | Jan 2025 | Official leaderboard | |
| 45 | CYFRAGOVPL/PLLuM-12B-base | 46.5% | Official leaderboard | ||
| 46 | meta-llama/Llama-2-70b-hf | 46.4% | Official leaderboard | ||
| 47 | CYFRAGOVPL/Llama-PLLuM-8B-base | 46.3% | Official leaderboard | ||
| 48 | | 45.6% | Jun 2024 | Official leaderboard | |
| 49 | mistralai/Mistral-Nemo-Instruct-2407 | 45.5% | Official leaderboard | ||
| 50 | meta-llama/Meta-Llama-3-8B-Instruct | 44.8% | Official leaderboard | ||
| 51 | | 44.2% | Jul 2024 | Official leaderboard | |
| 52 | | 44.2% | Mar 2025 | Official leaderboard | |
| 53 | mistralai/Ministral-8B-Instruct-2410 | 42.3% | Official leaderboard | ||
| 54 | | 42.2% | Jul 2024 | Official leaderboard | |
| 55 | allenai/OLMo-2-0325-32B | 41.8% | Official leaderboard | ||
| 56 | mistralai/Mistral-7B-Instruct-v0.3 | 41.7% | Official leaderboard | ||
| 57 | 01-ai/Yi-1.5-34B-Chat | 41.5% | Official leaderboard | ||
| 58 | 01-ai/Yi-34B-Chat | 41.4% | Official leaderboard | ||
| 59 | | 41.4% | Apr 2024 | Official leaderboard | |
| 60 | | 41.1% | May 2024 | Official leaderboard | |
| 61 | speakleash/Bielik-7B-Instruct-v0.1 | 40.8% | Official leaderboard | ||
| 62 | | 40.8% | Dec 2023 | Official leaderboard | |
| 63 | 01-ai/Yi-34B-Chat-4bits | 40.3% | Official leaderboard | ||
| 64 | Voicelab/trurl-2-13b-8bit | 40.2% | Official leaderboard | ||
| 65 | Voicelab/trurl-2-13b | 40.2% | Official leaderboard | ||
| 66 | | 39.9% | Apr 2025 | Official leaderboard | |
| 67 | meta-llama/Llama-3.2-3B-Instruct | 39.9% | Official leaderboard | ||
| 68 | speakleash/Bielik-7B-v0.1 | 39.1% | Official leaderboard | ||
| 69 | lucyknada/microsoft_WizardLM-2-7B | 38.2% | Official leaderboard | ||
| 70 | | 37.8% | Sep 2023 | Official leaderboard | |
| 71 | | 37.6% | May 2024 | Official leaderboard | |
| 72 | 01-ai/Yi-34B-200K | 37.6% | Official leaderboard | ||
| 73 | | 37.1% | Sep 2023 | Official leaderboard | |
| 74 | 01-ai/Yi-1.5-9B | 37.1% | Official leaderboard | ||
| 75 | | 36% | Sep 2023 | Official leaderboard | |
| 76 | Voicelab/trurl-2-13b-academic | 34.9% | Official leaderboard | ||
| 77 | OPI-PG/Qra-13b | 34.9% | Official leaderboard | ||
| 78 | | 34.2% | Jun 2024 | Official leaderboard | |
| 79 | meta-llama/Llama-2-13b-hf | 33.9% | Official leaderboard | ||
| 80 | | 33.4% | Apr 2024 | Official leaderboard | |
| 81 | allenai/OLMo-2-1124-13B-Instruct | 33.2% | Official leaderboard | ||
| 82 | allenai/OLMo-2-1124-13B | 32.6% | Official leaderboard | ||
| 83 | Voicelab/trurl-2-7b | 32.3% | Official leaderboard | ||
| 84 | Voicelab/trurl-2-7b-8bit | 31.9% | Official leaderboard | ||
| 85 | meta-llama/Llama-3.2-1B-Instruct | 31.6% | Official leaderboard | ||
| 86 | allenai/OLMo-2-1124-7B-Instruct | 31.5% | Official leaderboard | ||
| 87 | allenai/OLMo-2-1124-7B | 31.1% | Official leaderboard | ||
| 88 | OPI-PG/Qra-7b | 29.1% | Official leaderboard | ||
| 89 | meta-llama/Llama-2-7b-hf | 28% | Official leaderboard | ||
| 90 | microsoft/phi-1 | 25.7% | Official leaderboard | ||
| 91 | utter-project/EuroLLM-1.7B-Instruct | 25.6% | Official leaderboard | ||
| 92 | | 25.6% | Dec 2023 | Official leaderboard | |
| 93 | OPI-PG/Qra-1b | 25.5% | Official leaderboard | ||
| 94 | sdadas/polish-gpt2-large | 24.9% | Official leaderboard | ||
| 95 | sdadas/polish-gpt2-medium | 24.4% | Official leaderboard | ||
| 96 | | 24.3% | Sep 2023 | Official leaderboard | |
| 97 | sdadas/polish-gpt2-small | 24.2% | Official leaderboard | ||
| 98 | sdadas/polish-gpt2-xl | 24% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 69.1% | Sep 2024 | Official leaderboard | |
| 2 | | 67.1% | Dec 2024 | Official leaderboard | |
| 3 | | 66.8% | Apr 2025 | Official leaderboard | |
| 4 | | 63.5% | Apr 2025 | Official leaderboard | |
| 5 | | 63.1% | Jul 2024 | Official leaderboard | |
| 6 | | 62.2% | Apr 2024 | Official leaderboard | |
| 7 | | 61% | Sep 2024 | Official leaderboard | |
| 8 | | 61% | Apr 2025 | Official leaderboard | |
| 9 | | 55.8% | Jan 2025 | Official leaderboard | |
| 10 | | 55.3% | Sep 2024 | Official leaderboard | |
| 11 | | 55.3% | Apr 2025 | Official leaderboard | |
| 12 | | 51.8% | Dec 2024 | Official leaderboard | |
| 13 | | 50.2% | Apr 2025 | Official leaderboard | |
| 14 | | 47.7% | Dec 2023 | Official leaderboard | |
| 15 | | 46.8% | Feb 2024 | Official leaderboard | |
| 16 | | 46.8% | Jan 2025 | Official leaderboard | |
| 17 | | 45.6% | Jun 2024 | Official leaderboard | |
| 18 | | 44.2% | Jul 2024 | Official leaderboard | |
| 19 | | 44.2% | Mar 2025 | Official leaderboard | |
| 20 | | 42.2% | Jul 2024 | Official leaderboard | |
| 21 | | 41.4% | Apr 2024 | Official leaderboard | |
| 22 | | 41.1% | May 2024 | Official leaderboard | |
| 23 | | 40.8% | Dec 2023 | Official leaderboard | |
| 24 | | 39.9% | Apr 2025 | Official leaderboard | |
| 25 | | 37.8% | Sep 2023 | Official leaderboard | |
| 26 | | 37.6% | May 2024 | Official leaderboard | |
| 27 | | 37.1% | Sep 2023 | Official leaderboard | |
| 28 | | 36% | Sep 2023 | Official leaderboard | |
| 29 | | 34.2% | Jun 2024 | Official leaderboard | |
| 30 | | 33.4% | Apr 2024 | Official leaderboard | |
| 31 | | 25.6% | Dec 2023 | Official leaderboard | |
| 32 | | 24.3% | Sep 2023 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LLMzSzŁ 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 LLMzSzŁ 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 19 months ago, in April 2025, for Qwen3-1.7B. 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 (98 entries).
- Pass Models scored 32 models we track, plus 66 other entries on its leaderboard.
- Warning Newest score The newest came 19 months ago, in April 2025, for Qwen3-1.7B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen3-32B (#135).
- Pass Headroom The best is 69.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 33 rows for models we track and 66 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.