List your company

Theorem-proving on MathOlympiad-Bench

46.7Pass@32LongCat-Flash-Prover
2.18813.74425.336.856Mar 22, 2026

Evaluation results

MethodLinks
LongCat-Flash-ProverMode=sketch-proof, Search Strategy=TIR & Tree Search, Budget (b)=1802026.0346.7
LongCat-Flash-ProverMode=sketch-proof, Search Strategy=TIR, Budget (b)=1802026.0342.5
LongCat-Flash-ProverEvaluation Mode=sketch-proof mode, TIR (Tool-Integrated Reasoning)=true2026.0335.8
LongCat-Flash-ProverEvaluation Mode=whole-proof mode, TIR (Tool-Integrated Reasoning)=true2026.0327.5
Goedel-Prover-V2-32BModel Category=Open-Weights Prover Models, Self-correction=true2026.0320.3
LongCat-Flash-ProverEvaluation Mode=whole-proof mode, TIR (Tool-Integrated Reasoning)=false2026.0316.9
Goedel-Prover-V2-32BModel Category=Open-Weights Prover Models, Self-correction=false2026.0316.7
Goedel-Prover-V2-32BBudget (b)=322026.0316.7
DeepSeek-V3.2Model Category=Open-Weights Reasoning Models2026.0314.7
DeepSeek-Prover-V2-671BModel Category=Open-Weights Prover Models2026.0313.9
Kimina-Prover-72BModel Category=Open-Weights Prover Models2026.0313.1
DeepSeek-Prover-V2-7BModel Category=Open-Weights Prover Models2026.0311.1
Goedel-Prover-V2-8BModel Category=Open-Weights Prover Models, Self-correction=false2026.0311.1
Kimina-Prover-8BModel Category=Open-Weights Prover Models2026.038.6
Kimi-K2.5Model Category=Open-Weights Reasoning Models2026.037.5
Gemini-3 ProModel Category=Close-Weights Reasoning Models2026.033.9