Question Answering on SuperGPQA
34.51Pass@1Qwen2.5-7B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-7B-InstructTraining Pipeline=PSFT → GRPO2025.08 | 34.51 | |
| Qwen2.5-7B-InstructTraining Pipeline=SFT → GRPO2025.08 | 33.8 | |
| Llama3.1-8B-InstructTraining Pipeline=PSFT → GRPO2025.08 | 31.3 | |
| Qwen2.5-7B-InstructTraining Pipeline=SFT2025.08 | 29.02 | |
| Qwen2.5-7B-InstructTraining Pipeline=PSFT2025.08 | 28.1 | |
| Llama3.1-8B-InstructTraining Pipeline=SFT → GRPO2025.08 | 27.8 | |
| Llama3.1-8B-InstructTraining Pipeline=PSFT2025.08 | 25.85 | |
| Llama3.1-8B-InstructTraining Pipeline=SFT2025.08 | 21.95 |