List your company

Mathematical Reasoning on AIME 2024 (Acc, GT-pass)

63.3AccuracyBASE
18.26829.95941.6553.341Jun 14, 2026

Evaluation results

MethodLinks
BASESolver=Gemini 3 Pro, K=82026.0663.3100
BASESolver=R1-Qwen3-8B, K=82026.0660.7100
Independent FormalizationSolver=R1-Qwen3-8B, K=82026.0644.873.7
Independent FormalizationSolver=Gemini 3 Pro, K=82026.064066.7
BASESolver=Qwen3-8B, K=82026.0620.7100
Independent FormalizationSolver=Qwen3-8B, K=82026.062085.7