List your company

Mathematical Theorem Proving on AMC-AIMO

16.2Proof-level AccuracyBASE
8.60810.57912.5514.521Jun 14, 2026

Evaluation results

MethodLinks
BASESolver=R1-Qwen3-8B, Evaluation Protocol=BASE, Prover=DeepSeek-Prover-V2, K=82026.0616.2
BASESolver=Gemini 3 Pro, Evaluation Protocol=BASE, Prover=DeepSeek-Prover-V2, K=82026.0613.3
BASESolver=Qwen3-8B, Evaluation Protocol=BASE, Prover=DeepSeek-Prover-V2, K=82026.068.9