Benchmark Almanac

MathCLUE

Gemini 2.5 Pro Mar 2025 92.5 leads since March 2025
Not in model cards

Models solve problems from Chinese high school math competitions.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Competition problems with answers
Level
Competition
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Subject
Mathematics
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
A host
Strongest model tested
o4-mini #95 on the capability index
Last model added
April 2025
Scores refreshed
November 20th, 2026
28
Entries on its own leaderboard, 20 models we track

Gemini 2.5 Pro leads with 92.5 among models released by April 2025 Gemini 2.5 Pro leads with 92.5 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:

  1. 1 Gemini 2.5 Pro Mar 2025, API 92.5
  2. 2 o4-mini high / API 91.5
  3. 3 QwQ-32B API 91.0
  4. 4 Qwen3-32B API 90.3
  5. 5 o3-mini high / API 89.5
  6. 6 DeepSeek-R1 API 87.3
  7. 7 Hunyuan-T1 API 87.3
  8. 8 Qwen3-235B-A22B API 85.7
  9. 9 Qwen3-30B-A3B API 85.1
  10. 10 QwQ-Max-Preview 网页 84.0
  11. 11 Gemini 2.0 Flash Thinking Jan 2025, API 80.6
  12. 12 o1 官网 77.6
  13. 13 GLM-Zero-Preview API 69.4
  14. 14 Claude 3.7 Sonnet POE 69.4
  15. 15 QwQ-32B-Preview API 67.9
  16. 16 DeepSeek-V3 Mar 2025, API 67.9
  17. 17 Deepseek-R1-Lite-Preview 官网 61.2
  18. 18 InternThinker 官网 60.5
  19. 19 GPT-4.1 API 50.6
  20. 20 Doubao-pro-32k-241215 API 48.5
  21. 21 讯飞星火 X1 官网 47.0
  22. 22 Llama 4 Maverick API 47.0
  23. 23 DeepSeek-V3 API 45.5
  24. 24 Gemini 2.0 Flash Dec 2024, 官网 44.8
  25. 25 360zhinao2 API 37.3
  26. 26 Qwen2.5-Max API 33.6
  27. 27 Llama 4 Scout API 24.6
  28. 28 Claude 3.5 Sonnet(20241022) POE 17.9

Source: Official MathCLUE leaderboard

#EntryScoreSettingReleasedRun onSource
1 Gemini 2.5 Pro Mar 2025 92.5 API Mar 2025 Mar 2025 Official leaderboard
2 o4-mini 91.5 high / API Apr 2025 Apr 2025 Official leaderboard
3 QwQ-32B 91.0 API Mar 2025 Mar 2025 Official leaderboard
4 Qwen3-32B 90.3 API Apr 2025 Apr 2025 Official leaderboard
5 o3-mini 89.5 high / API Jan 2025 Feb 2025 Official leaderboard
6 DeepSeek-R1 87.3 API Jan 2025 Feb 2025 Official leaderboard
7 Hunyuan-T1 87.3 API Mar 2025 Apr 2025 Official leaderboard
8 Qwen3-235B-A22B 85.7 API Apr 2025 Apr 2025 Official leaderboard
9 Qwen3-30B-A3B 85.1 API Apr 2025 Apr 2025 Official leaderboard
10 QwQ-Max-Preview 84.0 网页 Feb 2025 Official leaderboard
11 Gemini 2.0 Flash Thinking Jan 2025 80.6 API Jan 2025 Feb 2025 Official leaderboard
12 o1 77.6 官网 Dec 2024 Jan 2025 Official leaderboard
13 GLM-Zero-Preview 69.4 API Jan 2025 Official leaderboard
14 Claude 3.7 Sonnet 69.4 POE Feb 2025 Feb 2025 Official leaderboard
15 QwQ-32B-Preview 67.9 API Nov 2024 Jan 2025 Official leaderboard
16 DeepSeek-V3 Mar 2025 67.9 API Mar 2025 Mar 2025 Official leaderboard
17 Deepseek-R1-Lite-Preview 61.2 官网 Jan 2025 Official leaderboard
18 InternThinker 60.5 官网 Jan 2025 Official leaderboard
19 GPT-4.1 50.6 API Apr 2025 Apr 2025 Official leaderboard
20 Doubao-pro-32k-241215 48.5 API Jan 2025 Official leaderboard
21 讯飞星火 X1 47.0 官网 Jan 2025 Official leaderboard
22 Llama 4 Maverick 47.0 API Apr 2025 Apr 2025 Official leaderboard
23 DeepSeek-V3 45.5 API Dec 2024 Jan 2025 Official leaderboard
24 Gemini 2.0 Flash Dec 2024 44.8 官网 Dec 2024 Jan 2025 Official leaderboard
25 360zhinao2 37.3 API Jan 2025 Official leaderboard
26 Qwen2.5-Max 33.6 API Jan 2025 Feb 2025 Official leaderboard
27 Llama 4 Scout 24.6 API Apr 2025 Apr 2025 Official leaderboard
28 Claude 3.5 Sonnet(20241022) 17.9 POE Jan 2025 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 Gemini 2.5 Pro Mar 2025 92.5 API Mar 2025 Mar 2025 Official leaderboard
2 o4-mini 91.5 high / API Apr 2025 Apr 2025 Official leaderboard
3 QwQ-32B 91.0 API Mar 2025 Mar 2025 Official leaderboard
4 Qwen3-32B 90.3 API Apr 2025 Apr 2025 Official leaderboard
5 o3-mini 89.5 high / API Jan 2025 Feb 2025 Official leaderboard
6 DeepSeek-R1 87.3 API Jan 2025 Feb 2025 Official leaderboard
7 Hunyuan-T1 87.3 API Mar 2025 Apr 2025 Official leaderboard
8 Qwen3-235B-A22B 85.7 API Apr 2025 Apr 2025 Official leaderboard
9 Qwen3-30B-A3B 85.1 API Apr 2025 Apr 2025 Official leaderboard
10 Gemini 2.0 Flash Thinking Jan 2025 80.6 API Jan 2025 Feb 2025 Official leaderboard
11 o1 77.6 官网 Dec 2024 Jan 2025 Official leaderboard
12 Claude 3.7 Sonnet 69.4 POE Feb 2025 Feb 2025 Official leaderboard
13 QwQ-32B-Preview 67.9 API Nov 2024 Jan 2025 Official leaderboard
14 DeepSeek-V3 Mar 2025 67.9 API Mar 2025 Mar 2025 Official leaderboard
15 GPT-4.1 50.6 API Apr 2025 Apr 2025 Official leaderboard
16 Llama 4 Maverick 47.0 API Apr 2025 Apr 2025 Official leaderboard
17 DeepSeek-V3 45.5 API Dec 2024 Jan 2025 Official leaderboard
18 Gemini 2.0 Flash Dec 2024 44.8 官网 Dec 2024 Jan 2025 Official leaderboard
19 Qwen2.5-Max 33.6 API Jan 2025 Feb 2025 Official leaderboard
20 Llama 4 Scout 24.6 API Apr 2025 Apr 2025 Official leaderboard

6 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen OpenAI DeepSeek Google DeepMind
Own leaderboard Not tested since Apr 2025

Source: Official MathCLUE leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
20.0 40.0 60.0 80.0 100.0 2025 20.0 40.0 60.0 80.0 100.0 2025

Source: Official MathCLUE 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 Math

All 140 in Math
  • AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
  • IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
  • HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
  • PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked. Qwen3.7-Max 86.5%
  • MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
  • MathArena Apex Shortlist In use Models solve 47 hard final-answer problems that MathArena selected from 2025 competitions, where the best models scored about 50% at selection. Scored by accuracy over repeated attempts. GPT-5.5 98.4%

Data audit

7 of 9 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the 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 (28 entries).
  • Pass Models scored 20 models we track, plus 8 other entries on its leaderboard.
  • Warning Newest score The newest came 19 months ago, in April 2025, for Qwen3-235B-A22B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o4-mini (#95).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 20 rows for models we track and 8 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.

How we check