Mathematics on AIME 2024, OmniMath, OlympiadBench, AMC 22-24, MATH-500
0.76CBRC ScoreOmniMath
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| OmniMathPrompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01 | 0.76 | 0.13 | 0.79 | 62 | 0.27 | 0.61 | 0.22 | 0.75 | |
| OlympiadBenchPrompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01 | 0.75 | 0.12 | 0.76 | 64 | 0.32 | 0.61 | 0.23 | 0.73 | |
| AMC 22-24Prompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01 | 0.7 | 0.18 | 0.36 | 1,667 | 0.11 | 0.46 | 0.09 | 0.55 | |
| MATH-500Prompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01 | 0.7 | 0.18 | 0.16 | 4,987 | 0.07 | 0.62 | 0.1 | 0.55 | |
| AIME 2024Prompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01 | 0.52 | 0.1 | 0.74 | 53 | 0.22 | 0.85 | 0.13 | 0.79 |