SuperCLUE-Math6
Models solve thousands of multi-step Chinese math word problems. Scores combine reasoning-step quality and accuracy into a comprehensive score and a reasoning level.
Reports give a comprehensive score, a reasoning-steps score, an overall accuracy score and a reasoning level from 1 to 5.
- Made by
- SuperCLUE
- Released
- January 2024
- Kind
- Word problems
- Level
- School
- Scored
- Graded by a model
- Answers
- Short answer
- Tasks
- All public
- Strongest model tested
- GPT-4 Turbo Nov 2023 #175 on the capability index
- Last in a system card
- May 2024
- Last model added
- May 2024
- Scores refreshed
- November 12th, 2026
In the authors’ words
We introduce SuperCLUE-Math6(SC-Math6), a new benchmark dataset to evaluate the mathematical reasoning abilities of Chinese language models. SC-Math6 is designed as an upgraded Chinese version of the GSM8K dataset with enhanced difficulty, diversity, and application scope. It consists of over 2000 mathematical word problems requiring multi-step reasoning and providing natural language solutions. We propose an innovative scheme to quantify the reasoning capability of large models based on performance over problems with different reasoning steps. Experiments on 13 representative Chinese models demonstrate a clear stratification of reasoning levels, with top models like GPT-4 showing superior performance. SC-Math6 fills the gap in Chinese mathematical reasoning benchmarks and provides a comprehensive testbed to advance the intelligence of Chinese language models.
DeepSeek-V2 (MoE-236B, May 2024) leads with 83.3
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
GPT-4 Turbo leads with 87.8 across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.
GPT-4 Turbo leads with 87.8, 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.
Source: Labs’ model cards
- 1 GPT-4 Turbo Nov 2023 87.8
- 2
Qwen-14B 49.0 - 3 Baichuan2-13B-Chat 36.8
- 4 ChatGLM3-6B 33.0
Source: Official SuperCLUE-Math6 leaderboard
- 1 GPT-4 Turbo Nov 2023 87.8
- 2
DeepSeek-V2 (MoE-236B, May 2024) 83.3 - 3 Qwen-14B 49.0
- 4 Baichuan2-13B-Chat 36.8
- 5 ChatGLM3-6B 33.0
Sources: Official SuperCLUE-Math6 leaderboard and labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DeepSeek-V2 (MoE-236B, May 2024) | 83.3 | May 2024 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo Nov 2023 | 87.8 | Nov 2023 | Official leaderboard | |
| 2 | Qwen-14B | 49.0 | Sep 2023 | Official leaderboard | |
| 3 | Baichuan2-13B-Chat | 36.8 | Sep 2023 | Official leaderboard | |
| 4 | ChatGLM3-6B | 33.0 | Oct 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo Nov 2023 | 87.8 | Nov 2023 | Official leaderboard | |
| 2 | DeepSeek-V2 (MoE-236B, May 2024) | 83.3 | May 2024 | Lab model card | |
| 3 | Qwen-14B | 49.0 | Sep 2023 | Official leaderboard | |
| 4 | Baichuan2-13B-Chat | 36.8 | Sep 2023 | Official leaderboard | |
| 5 | ChatGLM3-6B | 33.0 | Oct 2023 | Official leaderboard |
The benchmark's own leaderboard has 11 entries, 4 of them models we track. Switch the scores above to rank them together.
Number one over time Number one over time Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SuperCLUE-Math6 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official SuperCLUE-Math6 leaderboard and labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
One system card reports it
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 |
|---|---|---|---|---|
| May 7, 2024 | DeepSeek-V2 (MoE-236B, May 2024) technical report | 83.3 | SC-Math6 Comprehensive Score, Reasoning Level 5, reasoning-steps score 85.73, overall accuracy score 84.54 (Table 11) | Capabilities |
More 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%