C-Eval
The official leaderboard hasn’t scored a model released after Claude 1.3 (April 2023). Labs report their own numbers for 46 newer models, such as Qwen3-Max-2026-01-23 at 93.7%.
13,948 Chinese multiple-choice exam questions across 52 disciplines and four difficulty levels. Accuracy.
Saturated. The maintainers released the full test set with answers on July 27th, 2025, so test scores are no longer held out.
- Released
- May 2023
- Kind
- Exam questions
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Mathematics, Computer and information sciences, Physical sciences, Biological sciences, Other social sciences
- Language
- Chinese
- Interaction
- Single turn
- Items from
- Exams and contests
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Biology and medicine
- Strongest model tested
-
DeepSeek V4.1 Flash #34 on the capability index
- Last in a launch post
- September 2026, dropped after it saturated
- Last model added
- September 2026
- Scores refreshed
- November 18th, 2026
In the authors’ words
New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. C-Eval comprises multiple-choice questions across four difficulty levels: middle school, high school, college, and professional. The questions span 52 diverse disciplines, ranging from humanities to science and engineering. C-Eval is accompanied by C-Eval Hard, a subset of very challenging subjects in C-Eval that requires advanced reasoning abilities to solve. We conduct a comprehensive evaluation of the most advanced LLMs on C-Eval, including both English- and Chinese-oriented models. Results indicate that only GPT-4 could achieve an average accuracy of over 60%, suggesting that there is still significant room for improvement for current LLMs. We anticipate C-Eval will help analyze important strengths and shortcomings of foundation models, and foster their development and growth for Chinese users.
Qwen3-Max-2026-01-23 leads with 93.7% among models released by September 2026
Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.
Claude 1.3 leads with 54.2% across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Dotted bars are reruns by Epoch AI or another board, and each row names its source.
Qwen3-Max-2026-01-23 leads with 93.7%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
The newest model with a score here came out in September 2026, and nobody has reported 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
- Claude Opus 5.5
- and 16 more
- 93.7
Qwen3-Max-2026-01-23
- 93.3
Qwen 3.6 Plus
- 93.1
DeepSeek-V4-Pro
- 93.0
Qwen3.5 397B-A17B
- 92.1
DeepSeek V4.1 Flash
- 92.1
DeepSeek-V4.1-Flash Base
- 92.0
Qwen3.5-Omni-Plus
- 91.9
Qwen3.5-122B-A10B
- 91.8
DeepSeek-R1
- 91.8
Hunyuan-T1
- 91.7
LongCat-Flash-Omni
- 91.5
Ring-1T
- 91.4
Qwen3.6 27B
- 90.9
Hunyuan-TurboS
- 90.9
InternVL3.5-241B-A28B
- 90.6
ERNIE-4.5-300B-A47B
- 90.5
Qwen3.5-27B
- 90.4
LongCat-Flash-Chat
- 90.2
Qwen3.5-35B-A3B
- 90.0
Qwen 3.6 35B-A3B
- 89.6
Qwen3-235B-A22B
- 89.2
Keye-VL-2.0-30B-A3B
- 88.8 GLM-5
- 88.3 Kimi k1.5
- 88.2
Qwen3-Coder-Next
- 88.2
Qwen3.5-9B
- 87.3
Qwen3-32B
- 86.9 GLM-4.5
- 86.6
Qwen3-30B-A3B
- 86.5
DeepSeek-V3
- 86.2
Qwen3-14B
- 85.1
Qwen3.5-4B
- 84.1
Qwen1.5-72B
- 83.8
Qwen2-72B
- 83.4
Qwen3-8B
- 78.0
DeepSeek-V2 (MoE-236B, May 2024)
- 77.5
Qwen3-4B
- 77.2 Moonlight-16B-A3B
- 73.2
Qwen3.5-2B
- 71.7
Qwen-14B
- 69.0 ChatGLM3-6B
- 68.1
Qwen3-1.7B
- 65.2
DeepSeek LLM 67B
- 59.7
Qwen-7B
- 50.7 Qwen-1_8B
- 50.5
Qwen3.5-0.8B
- 1
Qwen3-Max-2026-01-23 93.7%
- 2
Qwen 3.6 Plus 93.3%
- 3
DeepSeek-V4-Pro 93.1%
- 4
Qwen3.5 397B-A17B 93%
- 5
DeepSeek V4.1 Flash 92.1%
- 6
DeepSeek-V4.1-Flash Base 92.1%
- 7
Qwen3.5-Omni-Plus 92%
- 8
Qwen3.5-122B-A10B 91.9%
- 9
DeepSeek-R1 91.8%
- 10
Hunyuan-T1 91.8%
- 11
LongCat-Flash-Omni 91.7%
- 12
Ring-1T 91.5%
- 13
Qwen3.6 27B 91.4%
- 14
Hunyuan-TurboS 90.9%
- 15
InternVL3.5-241B-A28B 90.9%
- 16
ERNIE-4.5-300B-A47B 90.6%
- 17
Qwen3.5-27B 90.5%
- 18
LongCat-Flash-Chat 90.4%
- 19
Qwen3.5-35B-A3B 90.2%
- 20
Qwen 3.6 35B-A3B 90%
- 21
Qwen3-235B-A22B 89.6%
- 22
Keye-VL-2.0-30B-A3B 89.2%
- 23 GLM-5 88.8%
- 24 Kimi k1.5 88.3%
- 25
Qwen3-Coder-Next 88.2%
- 26
Qwen3.5-9B 88.2%
- 27
Qwen3-32B 87.3%
- 28 GLM-4.5 86.9%
- 29
Qwen3-30B-A3B 86.6%
- 30
DeepSeek-V3 86.5%
- 31
Qwen3-14B 86.2%
- 32
Qwen3.5-4B 85.1%
- 33
Qwen1.5-72B 84.1%
- 34
Qwen2-72B 83.8%
- 35
Qwen3-8B 83.4%
- 36
DeepSeek-V2 (MoE-236B, May 2024) 78%
- 37
Qwen3-4B 77.5%
- 38 Moonlight-16B-A3B 77.2%
- 39
Qwen3.5-2B 73.2%
- 40
Qwen-14B 71.7%
- 41 ChatGLM3-6B 69%
- 42
Qwen3-1.7B 68.1%
- 43
DeepSeek LLM 67B 65.2%
- 44
Qwen-7B 59.7%
- 45 Qwen-1_8B 50.7%
- 46
Qwen3.5-0.8B 50.5%
Source: Labs’ model cards
- 1 Claude 1.3 Five-shot 54.2%
- 2 ChatGLM-6B Zero-shot 38.9%
- 3
LLaMA-65B Five-shot 38.8%
Source: Official C-Eval leaderboard
- 93.7
Qwen3-Max-2026-01-23
- 93.3
Qwen 3.6 Plus
- 93.1
DeepSeek-V4-Pro
- 93.0
Qwen3.5 397B-A17B
- 92.1
DeepSeek V4.1 Flash
- 92.1
DeepSeek-V4.1-Flash Base
- 92.0
Qwen3.5-Omni-Plus
- 91.9
Qwen3.5-122B-A10B
- 91.8
DeepSeek-R1
- 91.8
Hunyuan-T1
- 91.7
LongCat-Flash-Omni
- 91.5
Ring-1T
- 91.4
Qwen3.6 27B
- 90.9
Hunyuan-TurboS
- 90.9
InternVL3.5-241B-A28B
- 90.6
ERNIE-4.5-300B-A47B
- 90.5
Qwen3.5-27B
- 90.4
LongCat-Flash-Chat
- 90.2
Qwen3.5-35B-A3B
- 90.0
Qwen 3.6 35B-A3B
- 89.6
Qwen3-235B-A22B
- 89.2
Keye-VL-2.0-30B-A3B
- 88.8 GLM-5
- 88.3 Kimi k1.5
- 88.2
Qwen3-Coder-Next
- 88.2
Qwen3.5-9B
- 87.3
Qwen3-32B
- 86.9 GLM-4.5
- 86.6
Qwen3-30B-A3B
- 86.5
DeepSeek-V3
- 86.2
Qwen3-14B
- 85.1
Qwen3.5-4B
- 84.1
Qwen1.5-72B
- 83.8
Qwen2-72B
- 83.4
Qwen3-8B
- 78.0
DeepSeek-V2 (MoE-236B, May 2024)
- 77.5
Qwen3-4B
- 77.2 Moonlight-16B-A3B
- 73.2
Qwen3.5-2B
- 71.7
Qwen-14B
- 69.0 ChatGLM3-6B
- 68.1
Qwen3-1.7B
- 65.2
DeepSeek LLM 67B
- 59.7
Qwen-7B
- 54.2 Claude 1.3
- 50.7 Qwen-1_8B
- 50.5
Qwen3.5-0.8B
- 38.9 ChatGLM-6B
- 38.8
LLaMA-65B
- 1
Qwen3-Max-2026-01-23 93.7%
- 2
Qwen 3.6 Plus 93.3%
- 3
DeepSeek-V4-Pro 93.1%
- 4
Qwen3.5 397B-A17B 93%
- 5
DeepSeek V4.1 Flash 92.1%
- 6
DeepSeek-V4.1-Flash Base 92.1%
- 7
Qwen3.5-Omni-Plus 92%
- 8
Qwen3.5-122B-A10B 91.9%
- 9
DeepSeek-R1 91.8%
- 10
Hunyuan-T1 91.8%
- 11
LongCat-Flash-Omni 91.7%
- 12
Ring-1T 91.5%
- 13
Qwen3.6 27B 91.4%
- 14
Hunyuan-TurboS 90.9%
- 15
InternVL3.5-241B-A28B 90.9%
- 16
ERNIE-4.5-300B-A47B 90.6%
- 17
Qwen3.5-27B 90.5%
- 18
LongCat-Flash-Chat 90.4%
- 19
Qwen3.5-35B-A3B 90.2%
- 20
Qwen 3.6 35B-A3B 90%
- 21
Qwen3-235B-A22B 89.6%
- 22
Keye-VL-2.0-30B-A3B 89.2%
- 23 GLM-5 88.8%
- 24 Kimi k1.5 88.3%
- 25
Qwen3-Coder-Next 88.2%
- 26
Qwen3.5-9B 88.2%
- 27
Qwen3-32B 87.3%
- 28 GLM-4.5 86.9%
- 29
Qwen3-30B-A3B 86.6%
- 30
DeepSeek-V3 86.5%
- 31
Qwen3-14B 86.2%
- 32
Qwen3.5-4B 85.1%
- 33
Qwen1.5-72B 84.1%
- 34
Qwen2-72B 83.8%
- 35
Qwen3-8B 83.4%
- 36
DeepSeek-V2 (MoE-236B, May 2024) 78%
- 37
Qwen3-4B 77.5%
- 38 Moonlight-16B-A3B 77.2%
- 39
Qwen3.5-2B 73.2%
- 40
Qwen-14B 71.7%
- 41 ChatGLM3-6B 69%
- 42
Qwen3-1.7B 68.1%
- 43
DeepSeek LLM 67B 65.2%
- 44
Qwen-7B 59.7%
- 45 Claude 1.3 Five-shot 54.2%
- 46 Qwen-1_8B 50.7%
- 47
Qwen3.5-0.8B 50.5%
- 48 ChatGLM-6B Zero-shot 38.9%
- 49
LLaMA-65B Five-shot 38.8%
Sources: Labs’ model cards and official C-Eval leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 93.7% | Jan 2026 | Lab model card | |
| 2 | | 93.3% | Apr 2026 | Lab model card | |
| 3 | | 93.1% | Apr 2026 | Lab model card | |
| 4 | | 93% | Feb 2026 | Lab model card | |
| 5 | | 92.1% | Sep 2026 | Lab model card | |
| 6 | | 92.1% | Sep 2026 | Lab model card | |
| 7 | | 92% | Mar 2026 | Lab model card | |
| 8 | | 91.9% | Feb 2026 | Lab model card | |
| 9 | | 91.8% | Jan 2025 | Lab model card | |
| 10 | | 91.8% | Mar 2025 | Lab model card | |
| 11 | | 91.7% | Oct 2025 | Lab model card | |
| 12 | | 91.5% | Oct 2025 | Lab model card | |
| 13 | | 91.4% | Apr 2026 | Lab model card | |
| 14 | | 90.9% | Feb 2025 | Lab model card | |
| 15 | | 90.9% | Aug 2025 | Lab model card | |
| 16 | | 90.6% | Jun 2025 | Lab model card | |
| 17 | | 90.5% | Feb 2026 | Lab model card | |
| 18 | | 90.4% | Aug 2025 | Lab model card | |
| 19 | | 90.2% | Feb 2026 | Lab model card | |
| 20 | | 90% | Apr 2026 | Lab model card | |
| 21 | | 89.6% | Apr 2025 | Lab model card | |
| 22 | | 89.2% | May 2026 | Lab model card | |
| 23 | GLM-5 | 88.8% | Feb 2026 | Lab model card | |
| 24 | Kimi k1.5 | 88.3% | Jan 2025 | Lab model card | |
| 25 | | 88.2% | Feb 2026 | Lab model card | |
| 26 | | 88.2% | Mar 2026 | Lab model card | |
| 27 | | 87.3% | May 2025 | Lab model card | |
| 28 | GLM-4.5 | 86.9% | Aug 2025 | Lab model card | |
| 29 | | 86.6% | May 2025 | Lab model card | |
| 30 | | 86.5% | Dec 2024 | Lab model card | |
| 31 | | 86.2% | May 2025 | Lab model card | |
| 32 | | 85.1% | Mar 2026 | Lab model card | |
| 33 | | 84.1% | Feb 2024 | Lab model card | |
| 34 | | 83.8% | Jun 2024 | Lab model card | |
| 35 | | 83.4% | May 2025 | Lab model card | |
| 36 | | 78% | May 2024 | Lab model card | |
| 37 | | 77.5% | May 2025 | Lab model card | |
| 38 | Moonlight-16B-A3B | 77.2% | Feb 2025 | Lab model card | |
| 39 | | 73.2% | Mar 2026 | Lab model card | |
| 40 | | 71.7% | Sep 2023 | Lab model card | |
| 41 | ChatGLM3-6B | 69% | Oct 2023 | Lab model card | |
| 42 | | 68.1% | May 2025 | Lab model card | |
| 43 | | 65.2% | Nov 2023 | Lab model card | |
| 44 | | 59.7% | Sep 2023 | Lab model card | |
| 45 | Qwen-1_8B | 50.7% | Sep 2023 | Lab model card | |
| 46 | | 50.5% | Mar 2026 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude 1.3 | 54.2% | Five-shot | Apr 2023 | Official leaderboard |
| 2 | ChatGLM-6B | 38.9% | Zero-shot | Mar 2023 | Official leaderboard |
| 3 | 38.8% | Five-shot | Feb 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | 93.7% | Jan 2026 | Lab model card | ||
| 2 | 93.3% | Apr 2026 | Lab model card | ||
| 3 | 93.1% | Apr 2026 | Lab model card | ||
| 4 | 93% | Feb 2026 | Lab model card | ||
| 5 | 92.1% | Sep 2026 | Lab model card | ||
| 6 | 92.1% | Sep 2026 | Lab model card | ||
| 7 | 92% | Mar 2026 | Lab model card | ||
| 8 | 91.9% | Feb 2026 | Lab model card | ||
| 9 | 91.8% | Jan 2025 | Lab model card | ||
| 10 | 91.8% | Mar 2025 | Lab model card | ||
| 11 | 91.7% | Oct 2025 | Lab model card | ||
| 12 | 91.5% | Oct 2025 | Lab model card | ||
| 13 | 91.4% | Apr 2026 | Lab model card | ||
| 14 | 90.9% | Feb 2025 | Lab model card | ||
| 15 | 90.9% | Aug 2025 | Lab model card | ||
| 16 | 90.6% | Jun 2025 | Lab model card | ||
| 17 | 90.5% | Feb 2026 | Lab model card | ||
| 18 | 90.4% | Aug 2025 | Lab model card | ||
| 19 | 90.2% | Feb 2026 | Lab model card | ||
| 20 | 90% | Apr 2026 | Lab model card | ||
| 21 | 89.6% | Apr 2025 | Lab model card | ||
| 22 | 89.2% | May 2026 | Lab model card | ||
| 23 | GLM-5 | 88.8% | Feb 2026 | Lab model card | |
| 24 | Kimi k1.5 | 88.3% | Jan 2025 | Lab model card | |
| 25 | 88.2% | Feb 2026 | Lab model card | ||
| 26 | 88.2% | Mar 2026 | Lab model card | ||
| 27 | 87.3% | May 2025 | Lab model card | ||
| 28 | GLM-4.5 | 86.9% | Aug 2025 | Lab model card | |
| 29 | 86.6% | May 2025 | Lab model card | ||
| 30 | 86.5% | Dec 2024 | Lab model card | ||
| 31 | 86.2% | May 2025 | Lab model card | ||
| 32 | 85.1% | Mar 2026 | Lab model card | ||
| 33 | 84.1% | Feb 2024 | Lab model card | ||
| 34 | 83.8% | Jun 2024 | Lab model card | ||
| 35 | 83.4% | May 2025 | Lab model card | ||
| 36 | 78% | May 2024 | Lab model card | ||
| 37 | 77.5% | May 2025 | Lab model card | ||
| 38 | Moonlight-16B-A3B | 77.2% | Feb 2025 | Lab model card | |
| 39 | 73.2% | Mar 2026 | Lab model card | ||
| 40 | 71.7% | Sep 2023 | Lab model card | ||
| 41 | ChatGLM3-6B | 69% | Oct 2023 | Lab model card | |
| 42 | 68.1% | May 2025 | Lab model card | ||
| 43 | 65.2% | Nov 2023 | Lab model card | ||
| 44 | 59.7% | Sep 2023 | Lab model card | ||
| 45 | Claude 1.3 | 54.2% | Five-shot | Apr 2023 | Official leaderboard |
| 46 | Qwen-1_8B | 50.7% | Sep 2023 | Lab model card | |
| 47 | 50.5% | Mar 2026 | Lab model card | ||
| 48 | ChatGLM-6B | 38.9% | Zero-shot | Mar 2023 | Official leaderboard |
| 49 | 38.8% | Five-shot | Feb 2023 | Official leaderboard |
The benchmark's own leaderboard has 13 entries, 3 of them models we track. Switch the scores above to rank them together.
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Social science, Humanities and Other. Claude 1.3 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Social science
3 models we track have a score here.
- 1 Claude 1.3 61.7%
- 2 ChatGLM-6B 48.3%
- 3
LLaMA-65B 45.6%
Humanities
3 models we track have a score here.
- 1 Claude 1.3 52.1%
- 2 ChatGLM-6B 41.3%
- 3
LLaMA-65B 36.1%
STEM
3 models we track have a score here.
- 1 Claude 1.3 51.9%
- 2
LLaMA-65B ↑1 37.8%
- 3 ChatGLM-6B ↓1 33.3%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official C-Eval leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude 1.3 | Five-shot | 54.2% | |||
| Claude 1.3 | Zero-shot | 50.5% | |||
| ChatGLM-6B | Zero-shot | 38.9% | |||
| Five-shot | 38.8% | ||||
| Zero-shot | 34.7% | ||||
| ChatGLM-6B | Five-shot | 34.5% |
5 models have held number one in labs’ own numbers since its release in May 2023 Number one over time 6 models have held number one with claims included since its release in May 2023
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official C-Eval leaderboard and labs’ model cards
DeepSeek’s own number for DeepSeek-V3 passed 85% in December 2024
That was 19 months after its release. By the same age, 32% of the benchmarks from 2023 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official C-Eval leaderboard and labs’ model cards
Labs headline it less often now, last in September 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out. Qwen accounts for 18 of the 36 releases that named it since 2024.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Sep 10, 2026 | 92.1 | C-Eval (EM) | |
| May 25, 2026 | 89.2 | C-Eval | |
| Apr 24, 2026 | 93.1 | C-Eval (EM) | |
| Apr 22, 2026 | 91.4 | C-Eval | |
| Apr 15, 2026 | 90 | C-Eval | |
| Apr 2, 2026 | 93.3 | C-Eval | |
| Mar 30, 2026 | 92 | C-Eval | |
| Mar 2, 2026 | 50.5 | C-Eval (Thinking) | |
| Mar 2, 2026 | 73.2 | C-Eval (Thinking) | |
| Mar 2, 2026 | 85.1 | C-Eval | |
| Mar 2, 2026 | 88.2 | C-Eval | |
| Feb 24, 2026 | 90.2 | C-Eval | |
| Feb 24, 2026 | 90.5 | C-Eval | |
| Feb 24, 2026 | 91.9 | C-Eval | |
| Feb 16, 2026 | 93 | C-Eval | |
| Feb 2, 2026 | 88.2 | C-Eval, 88.2 | |
| Jan 23, 2026 | 93.7 | C-Eval | |
| Oct 31, 2025 | 91.7 | CEval(acc) | |
| Aug 29, 2025 | 90.4 | CEval(acc) | |
| Aug 25, 2025 | 90.9 | C-Eval | |
| Jun 30, 2025 | 90.6 | C-Eval | |
| Apr 29, 2025 | 89.6 | C-Eval | |
| Mar 21, 2025 | 91.8 | CEval | |
| Mar 16, 2025 | C-Eval | ||
| Feb 27, 2025 | 90.9 | C-Eval | |
| Feb 22, 2025 | Moonlight-16B-A3B | 77.2 | C-Eval |
| Jan 28, 2025 | C-Eval | ||
| Jan 20, 2025 | Kimi k1.5 | 88.3 | C-Eval (EM), short-CoT |
| Jan 20, 2025 | 91.8 | C-Eval (EM) | |
| Dec 26, 2024 | 86.5 | C-Eval (EM) | |
| Jun 7, 2024 | 83.8 | C-Eval | |
| May 7, 2024 | 78 | C-Eval | |
| Feb 5, 2024 | 84.1 | C-Eval | |
| Nov 29, 2023 | 65.2 | C-Eval | |
| Oct 27, 2023 | ChatGLM3-6B | 69 | C-Eval |
| Sep 25, 2023 | 71.7 | C-Eval (val, 5-shot) |
26 system cards report it, from 9 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Sep 10, 2026 | | 92.1 | C-Eval, EM, 5-shot | Capabilities |
| Jun 9, 2026 | | 89.2 | C-Eval (Figure 5, printed value) | Capabilities |
| Apr 17, 2026 | | 92 | C-Eval (Table 4) | Capabilities |
| Feb 17, 2026 | GLM-5 technical report | 88.8 | GLM-5-Base, C-Eval (EM) (Table 11) | Capabilities |
| Oct 31, 2025 | | 91.7 | CEval (acc) (Table 13) | Capabilities |
| Oct 21, 2025 | | 91.5 | C-Eval (Table 1) | Capabilities |
| Sep 1, 2025 | | 90.4 | CEval (acc) (Table 3) | Capabilities |
| Aug 25, 2025 | | 90.9 | C-Eval (Table 2, Table 14) | Capabilities |
| Aug 8, 2025 | GLM-4.5 technical report | 86.9 | GLM-4.5-Base, C-Eval (EM) (Table 2) | Capabilities |
| Jun 29, 2025 | | 90.6 | C-Eval (Table 5) | Capabilities |
| May 14, 2025 | | 83.4 | C-Eval, thinking mode (Table 17). Non-thinking 77.9 (Table 18) | Capabilities |
| May 14, 2025 | | 77.5 | C-Eval, thinking mode (Table 17). Non-thinking 72.2 (Table 18) | Capabilities |
| May 14, 2025 | | 87.3 | C-Eval, thinking mode (Table 13). Non-thinking 83.3 (Table 14) | Capabilities |
| May 14, 2025 | | 86.6 | C-Eval, thinking mode (Table 15). Non-thinking 82.9 (Table 16) | Capabilities |
| May 14, 2025 | | 89.6 | C-Eval, thinking mode (Table 11). Non-thinking 86.1 (Table 12) | Capabilities |
| May 14, 2025 | | 86.2 | C-Eval, thinking mode (Table 15). Non-thinking 81.0 (Table 16) | Capabilities |
| May 14, 2025 | | 68.1 | C-Eval, thinking mode (Table 19). Non-thinking 61.0 (Table 20) | Capabilities |
| Jan 20, 2025 | Kimi k1.5 technical report | 88.3 | C-Eval (EM), short-CoT (Table 3) | Capabilities |
| Jan 20, 2025 | | 91.8 | C-Eval (EM), DeepSeek-R1 (Table 8, same as final column of Table 3) | Capabilities |
| Dec 26, 2024 | | 86.5 | C-Eval (EM), DeepSeek-V3 (Table 6) | Capabilities |
| Jun 18, 2024 | ChatGLM3-6B technical report | 69 | ChatGLM3-6B-Base, C-Eval (Table 1) | Capabilities |
| May 7, 2024 | | 78 | C-Eval 5-shot, DeepSeek-V2 Chat (RL) (Table 3) | Capabilities |
| Jan 5, 2024 | | 65.2 | C-Eval 0-shot, DeepSeek 67B Chat (Table 6) | Capabilities |
| Sep 28, 2023 | | 59.7 | C-Eval 0-shot, higher of the two settings, 5-shot 59.3 (Table 5) | Capabilities |
| Sep 28, 2023 | | 71.7 | C-Eval 5-shot, higher of the two settings, 0-shot 69.8 (Table 5) | Capabilities |
| Sep 28, 2023 | | 50.7 | C-Eval 0-shot, higher of the two settings, 5-shot 50.3 (Table 5) | Capabilities |
More in Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (13 entries), launch posts (34 scores) and system cards (26 scores).
- Pass Models scored 49 models we track, plus 10 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for DeepSeek V4.1 Flash.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is DeepSeek V4.1 Flash (#34).
- Note Headroom Saturated. The best is 93.7%, past 85% since December 2024.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 6 rows for models we track and 10 other entries at the last read.
- Pass Last read November 18th, 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.