BrokenArXiv
Models are asked to prove statements from recent arXiv papers that were changed to be plausible but false. Full credit goes to models that say the statement is false.
MathArena releases a new set each month. The August 2026 set brought harder disproven conjectures, tool harnesses and a 0 to 3 grade. Scores from before and after that change do not compare.
- Released
- March 2026
- Kind
- Research mathematics
- Level
- Research frontier
- Scored
- Graded by a model
- Answers
- Written proof
- Tasks
- All public
- Strongest model tested
- Claude Opus 5.5 #4 on the capability index
- Last in a launch post
- August 2026
- Last model added
- October 2026
- Scores refreshed
- November 12th, 2026
GPT-6.1 Sol leads with 83.1%
Best score per entry from the benchmark's own leaderboard, read on November 12th, 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.
GPT-6.1 Sol leads with 83.1%, 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.
- 1 GPT-6.1 Sol max 83.1%
- 2 Claude Opus 5.5 high 77.3%
- 3 Inkling 2 Small (0.99) 63.2%
- 4 Kimi K3.1 Pro max 61.9%
- 5
DeepSeek V4.1 Flash 1017 max, dsh 48.7% - 6
Gemini 4 Argon high 47.9% - 7
Muse Spark Open xhigh 30.1%
Source: Official BrokenArXiv leaderboard
- 1 GPT-6.1 Sol max 83.1%
- 2 Claude Opus 5.5 high 77.3%
- 3 Kimi K3.1 Pro max 61.9%
- 4
Tencent Hy4 preview 54.6% - 5 DeepSeek V4.1 Flash 1017 max, dsh 48.7%
- 6 Gemini 4 Argon high 47.9%
- 7 Muse Spark Open xhigh 30.1%
Sources: Official BrokenArXiv leaderboard and labs’ model cards
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | 83.1% | max | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 77.3% | high | Sep 2026 | Official leaderboard |
| 3 | Inkling 2 Small (0.99) | 63.2% | Official leaderboard | ||
| 4 | Kimi K3.1 Pro | 61.9% | max | Oct 2026 | Official leaderboard |
| 5 | DeepSeek V4.1 Flash 1017 | 48.7% | max, dsh | Oct 2026 | Official leaderboard |
| 6 | Gemini 4 Argon | 47.9% | high | Sep 2026 | Official leaderboard |
| 7 | Muse Spark Open | 30.1% | xhigh | Oct 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | 83.1% | max | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 77.3% | high | Sep 2026 | Official leaderboard |
| 3 | Kimi K3.1 Pro | 61.9% | max | Oct 2026 | Official leaderboard |
| 4 | Tencent Hy4 preview | 54.6% | Aug 2026 | Lab model card | |
| 5 | DeepSeek V4.1 Flash 1017 | 48.7% | max, dsh | Oct 2026 | Official leaderboard |
| 6 | Gemini 4 Argon | 47.9% | high | Sep 2026 | Official leaderboard |
| 7 | Muse Spark Open | 30.1% | xhigh | Oct 2026 | Official leaderboard |
Labs report scores for 1 model in their cards. Switch the scores above to rank them together.
2 models have held number one on the official leaderboard since its release in March 2026 3 models have held number one with claims included since its release in March 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official BrokenArXiv 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 BrokenArXiv leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Aug 28, 2026 | Tencent Hy4 preview | 54.6 | BrokenArXiv |
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%