ArXivLean 09/2026
Math
This MathArena track asks models to prove or disprove 53 conjectures formalized in Lean 4.34.1 from September 2026 arXiv papers; a submission states its verdict by proving either the conjecture or its negation, and a problem counts only if that Lean proof passes MathArena's checker. Earlier ArXivLean releases asked only for proofs, so this prove-or-disprove protocol is its own factor group. Scores average observed problem attempts; the item count records distinct problems, not a single-run binomial denominator.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 47.2 |
| Gemini 4 Argon | 39.6 |
| GPT-6 Astra | 37.7 |
| GPT-6.1 Sol | 35.9 |
| DeepSeek V4.1 Flash | 5.7 |