List your company

Question Answering on SuperGPQA

34.51Pass@1Qwen2.5-7B-Instruct
21.447624.838828.2331.6212Aug 25, 2025

Evaluation results

MethodLinks
Qwen2.5-7B-InstructTraining Pipeline=PSFT → GRPO2025.0834.51
Qwen2.5-7B-InstructTraining Pipeline=SFT → GRPO2025.0833.8
Llama3.1-8B-InstructTraining Pipeline=PSFT → GRPO2025.0831.3
Qwen2.5-7B-InstructTraining Pipeline=SFT2025.0829.02
Qwen2.5-7B-InstructTraining Pipeline=PSFT2025.0828.1
Llama3.1-8B-InstructTraining Pipeline=SFT → GRPO2025.0827.8
Llama3.1-8B-InstructTraining Pipeline=PSFT2025.0825.85
Llama3.1-8B-InstructTraining Pipeline=SFT2025.0821.95