Auto-formalization on MathOlympiad-Bench
99.2Pass@8LongCat-Flash-Prover
Evaluation Results
| Method | Links | |
|---|---|---|
| LongCat-Flash-Proverw/ TIR=true2026.03 | 99.2 | |
| Claude-Opus-4.52026.03 | 94.4 | |
| LongCat-Flash-Prover2026.03 | 93.3 | |
| Gemini-3 Pro2026.03 | 93.1 | |
| Kimi-K2.52026.03 | 91.1 | |
| Goedel-V2-Formalizer-32B2026.03 | 89.2 | |
| DeepSeek-V3.22026.03 | 85.6 | |
| ATF-32B2026.03 | 83.6 | |
| StepFun-Formalizer-32B2026.03 | 78.6 | |
| ATF-8B-Distilled2026.03 | 76.7 | |
| Goedel-V2-Formalizer-8B2026.03 | 73.2 | |
| StepFun-Formalizer-7B2026.03 | 71.9 | |
| Kimina-Autoformalizer-7B2026.03 | 33.3 |