Coding on LeetCodeBench
58.9Pass@1GPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.03 | 58.9 | |
| Eurus-2-7B-PRIME-R-TAPtraining=R-TAP integrated2026.03 | 38.6 | |
| Llama-3.1-70B-Inst.2026.03 | 35 | |
| Eurus-2-7B-PRIME2026.03 | 31.1 | |
| RLOO2026.03 | 28.3 | |
| Eurus-2-7B-SFT2026.03 | 21.7 | |
| Qwen2.5-Math-7B-Inst.2026.03 | 11.7 |