Auto-formalization on FormalMath-Lite
99.8Pass@8LongCat-Flash-Prover
Evaluation Results
| Method | Links | |
|---|---|---|
| LongCat-Flash-Proverw/ TIR=true2026.03 | 99.8 | |
| LongCat-Flash-Prover2026.03 | 98.6 | |
| Goedel-V2-Formalizer-8B2026.03 | 98.1 | |
| Goedel-V2-Formalizer-32B2026.03 | 98.1 | |
| Kimi-K2.52026.03 | 97.9 | |
| Claude-Opus-4.52026.03 | 97.9 | |
| Gemini-3 Pro2026.03 | 97.4 | |
| ATF-8B-Distilled2026.03 | 95.5 | |
| DeepSeek-V3.22026.03 | 95.2 | |
| ATF-32B2026.03 | 94.3 | |
| StepFun-Formalizer-32B2026.03 | 90.9 | |
| StepFun-Formalizer-7B2026.03 | 88 | |
| Kimina-Autoformalizer-7B2026.03 | 86.8 |