Theorem-proving on MathOlympiad-Bench
46.7Pass@32LongCat-Flash-Prover
Evaluation Results
| Method | Links | |
|---|---|---|
| LongCat-Flash-ProverMode=sketch-proof, Search Strategy=TIR & Tree Search, Budget (b)=1802026.03 | 46.7 | |
| LongCat-Flash-ProverMode=sketch-proof, Search Strategy=TIR, Budget (b)=1802026.03 | 42.5 | |
| LongCat-Flash-ProverEvaluation Mode=sketch-proof mode, TIR (Tool-Integrated Reasoning)=true2026.03 | 35.8 | |
| LongCat-Flash-ProverEvaluation Mode=whole-proof mode, TIR (Tool-Integrated Reasoning)=true2026.03 | 27.5 | |
| Goedel-Prover-V2-32BModel Category=Open-Weights Prover Models, Self-correction=true2026.03 | 20.3 | |
| LongCat-Flash-ProverEvaluation Mode=whole-proof mode, TIR (Tool-Integrated Reasoning)=false2026.03 | 16.9 | |
| Goedel-Prover-V2-32BModel Category=Open-Weights Prover Models, Self-correction=false2026.03 | 16.7 | |
| Goedel-Prover-V2-32BBudget (b)=322026.03 | 16.7 | |
| DeepSeek-V3.2Model Category=Open-Weights Reasoning Models2026.03 | 14.7 | |
| DeepSeek-Prover-V2-671BModel Category=Open-Weights Prover Models2026.03 | 13.9 | |
| Kimina-Prover-72BModel Category=Open-Weights Prover Models2026.03 | 13.1 | |
| DeepSeek-Prover-V2-7BModel Category=Open-Weights Prover Models2026.03 | 11.1 | |
| Goedel-Prover-V2-8BModel Category=Open-Weights Prover Models, Self-correction=false2026.03 | 11.1 | |
| Kimina-Prover-8BModel Category=Open-Weights Prover Models2026.03 | 8.6 | |
| Kimi-K2.5Model Category=Open-Weights Reasoning Models2026.03 | 7.5 | |
| Gemini-3 ProModel Category=Close-Weights Reasoning Models2026.03 | 3.9 |