| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Putnam-Bench | LongCat-Flash-Prover | Pass@898.1 | 13 | 4mo ago | |
| Prover-Bench | LongCat-Flash-Prover | Pass@8100 | 13 | 4mo ago | |
| ProofNet (test) | LongCat-Flash-Prover | Pass@897.9 | 13 | 4mo ago | |
| MiniF2F (test) | LongCat-Flash-Prover | Pass@8100 | 13 | 4mo ago | |
| MathOlympiad-Bench | LongCat-Flash-Prover | Pass@899.2 | 13 | 4mo ago | |
| FormalMath-Lite | LongCat-Flash-Prover | Pass@899.8 | 13 | 4mo ago | |
| CombiBench | LongCat-Flash-Prover | Pass@897 | 13 | 4mo ago | |
| Conjectures | Aria | Final Accuracy42.9 | 9 | 22d ago | |
| FATE-X | Aria | Compiler Success Rate69 | 9 | 22d ago | |
| FATE-H | Goedel-V2 | Compiler Success Rate91 | 9 | 22d ago | |
| ProofNet | Aria | Compiler Success Rate91.6 | 5 | 22d ago |