Mathematical Reasoning on AIME 2024 (Avg@16 Accuracy and ATC)
37.1Avg@16 AccuracyAdaTIR-7B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AdaTIR-7BBackbone=Qwen2.5-7B, Training Strategy=AdaTIR2026.01 | 37.1 | 1.45 | |
| Qwen2.5-7B-Instruct (GRPO)Backbone=Qwen2.5-7B, Training Strategy=GRPO2026.01 | 33.8 | 2.02 | |
| AdaTIR-3BBackbone=Qwen2.5-3B, Training Strategy=AdaTIR2026.01 | 29.2 | 1.63 | |
| Qwen2.5-3B-Instruct (GRPO)Backbone=Qwen2.5-3B, Training Strategy=GRPO2026.01 | 26.3 | 2.52 | |
| Qwen2.5-7B-InstructBackbone=Qwen2.5-7B, Training Strategy=Instruct2026.01 | 12.3 | — | |
| Qwen2.5-3B-InstructBackbone=Qwen2.5-3B, Training Strategy=Instruct2026.01 | 10 | — | |
| Qwen2.5-3B-Instruct-TIRBackbone=Qwen2.5-3B, Training Strategy=TIR2026.01 | 6 | 0.79 | |
| Qwen2.5-7B-Instruct-TIRBackbone=Qwen2.5-7B, Training Strategy=TIR2026.01 | 5 | 0.48 |