Mathematical Reasoning on AIME 2024 (Acc, GT-pass)
63.3AccuracyBASE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BASESolver=Gemini 3 Pro, K=82026.06 | 63.3 | 100 | |
| BASESolver=R1-Qwen3-8B, K=82026.06 | 60.7 | 100 | |
| Independent FormalizationSolver=R1-Qwen3-8B, K=82026.06 | 44.8 | 73.7 | |
| Independent FormalizationSolver=Gemini 3 Pro, K=82026.06 | 40 | 66.7 | |
| BASESolver=Qwen3-8B, K=82026.06 | 20.7 | 100 | |
| Independent FormalizationSolver=Qwen3-8B, K=82026.06 | 20 | 85.7 |