List your company

Mathematical Theorem Proving on AIME 2024

6.9Proof-level AccuracyBASE
3.4684.3595.256.141Jun 14, 2026

Evaluation results

MethodLinks
BASESolver=Qwen3-8B, Evaluation Protocol=BASE, Prover=DeepSeek-Prover-V2, K=82026.066.9
BASESolver=Gemini 3 Pro, Evaluation Protocol=BASE, Prover=DeepSeek-Prover-V2, K=82026.066.7
BASESolver=R1-Qwen3-8B, Evaluation Protocol=BASE, Prover=DeepSeek-Prover-V2, K=82026.063.6