Mathematical Reasoning on AMC (accuracy)
57.5Accuracy (AMC)Eurus-2-7B-PRIME-R-TAP
Evaluation Results
| Method | Links | |
|---|---|---|
| Eurus-2-7B-PRIME-R-TAPtraining=R-TAP integrated2026.03 | 57.5 | |
| Qwen2.5-Math-7B-Inst.2026.03 | 50.6 | |
| Eurus-2-7B-PRIME2026.03 | 50.6 | |
| RLOO2026.03 | 47 | |
| GPT-4o2026.03 | 45.8 | |
| Llama-3.1-70B-Inst.2026.03 | 37.3 | |
| Eurus-2-7B-SFT2026.03 | 30.1 |