Mathematical Reasoning on AIME 2024 (Accuracy, ECE, Brier, AUROC)
20.8AccuracyCAR (MSCR)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CAR (MSCR)Model=Qwen2.5-3B2026.01 | 20.8 | 0.573 | 0.485 | 0.548 | |
| Vanilla SimpleTIRModel=Qwen2.5-3B2026.01 | 18.2 | 0.692 | 0.63 | 0.489 |
| Method | Links | ||||
|---|---|---|---|---|---|
| CAR (MSCR)Model=Qwen2.5-3B2026.01 | 20.8 | 0.573 | 0.485 | 0.548 | |
| Vanilla SimpleTIRModel=Qwen2.5-3B2026.01 | 18.2 | 0.692 | 0.63 | 0.489 |