Mathematical Reasoning On Aime24
Metrics
Acc
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Acc |
|---|---|
| qwen2-5-technical-report | 23.3 |
| search-o1-agentic-search-enhanced-large | 56.7 |
| Model 3 | 74.4 |
| Model 4 | 44.6 |
| Model 5 | 16 |
| Model 6 | 70.0 |
| s1-simple-test-time-scaling | 56.7 |
| deepseek-r1-incentivizing-reasoning | 79.8 |