Auto-formalization on Putnam-Bench
98.1Pass@8LongCat-Flash-Prover
Evaluation Results
| Method | Links | |
|---|---|---|
| LongCat-Flash-Proverw/ TIR=true2026.03 | 98.1 | |
| Claude-Opus-4.52026.03 | 93.5 | |
| Gemini-3 Pro2026.03 | 90.8 | |
| LongCat-Flash-Prover2026.03 | 89.9 | |
| Goedel-V2-Formalizer-32B2026.03 | 85.9 | |
| Kimi-K2.52026.03 | 82.8 | |
| Goedel-V2-Formalizer-8B2026.03 | 80.4 | |
| ATF-32B2026.03 | 77.5 | |
| ATF-8B-Distilled2026.03 | 70.7 | |
| StepFun-Formalizer-32B2026.03 | 65.1 | |
| Kimina-Autoformalizer-7B2026.03 | 59.3 | |
| StepFun-Formalizer-7B2026.03 | 55.4 | |
| DeepSeek-V3.22026.03 | 46.7 |