Mathematical Reasoning on AMC 2024 (test)
49.3Pass@1RLAD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RLADModel=Qwen3-1.7B, Context=8K2026.02 | 49.3 | 71.5 | |
| RLADModel=Qwen2.5-1.5B-DS, Context=8K2026.02 | 49.2 | 70.8 | |
| Qwen2.5-1.5B-DSTraining=GRPO, Context=8K2026.02 | 47.9 | 70.5 | |
| Qwen2.5-1.5B-DSTraining=KDRL, Context=8K2026.02 | 47.5 | 70.7 | |
| Qwen3-1.7BTraining=KDRL, Context=8K2026.02 | 47.2 | 65.6 | |
| Qwen3-1.7BTraining=GRPO, Context=8K2026.02 | 46.9 | 59.6 | |
| Qwen3-1.7BTraining=-, Context=8K2026.02 | 36.7 | 54.8 | |
| Qwen2.5-1.5B-DSTraining=-, Context=8K2026.02 | 36 | 60.7 |