Question Answering on ARC-C (avg.@8)
92.42Accuracy (ARC-C avg.@8)Qwen2.5-7B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-7B-InstructTraining Pipeline=PSFT → GRPO2025.08 | 92.42 | |
| Qwen2.5-7B-InstructTraining Pipeline=PSFT2025.08 | 92.29 | |
| Qwen2.5-7B-InstructTraining Pipeline=SFT → GRPO2025.08 | 92.25 | |
| Qwen2.5-7B-InstructTraining Pipeline=SFT2025.08 | 92.22 | |
| Llama3.1-8B-InstructTraining Pipeline=PSFT → GRPO2025.08 | 90.92 | |
| Llama3.1-8B-InstructTraining Pipeline=PSFT2025.08 | 89.11 | |
| Llama3.1-8B-InstructTraining Pipeline=SFT → GRPO2025.08 | 88.57 | |
| Llama3.1-8B-InstructTraining Pipeline=SFT2025.08 | 87.73 |