Mathematical Reasoning on AIME 2024 (Pass rate)
63.2Pass RateEVOTD
Evaluation Results
| Method | Links | |
|---|---|---|
| EVOTDEvaluation Protocol=Pass@8, Training Iteration=Iter32026.05 | 63.2 | |
| EVOTDEvaluation Protocol=Pass@8, Training Iteration=Iter22026.05 | 61.4 | |
| EVOTDEvaluation Protocol=Pass@8, Training Iteration=Iter12026.05 | 60.2 | |
| Qwen3-4B (Thinking)Evaluation Protocol=Pass@82026.05 | 55.4 | |
| Evol-InstructEvaluation Protocol=Pass@82026.05 | 55 | |
| EVOTDEvaluation Protocol=Pass@1, Training Iteration=Iter32026.05 | 42.2 | |
| EVOTDEvaluation Protocol=Pass@1, Training Iteration=Iter22026.05 | 37.9 | |
| EVOTDEvaluation Protocol=Pass@1, Training Iteration=Iter12026.05 | 36.7 | |
| Evol-InstructEvaluation Protocol=Pass@12026.05 | 35.4 | |
| Qwen3-4B (Thinking)Evaluation Protocol=Pass@12026.05 | 34 |