List your company

Astronomy Question Answering on AstroQA Chinese

62.4Pass@1Qwen2.5-7B + GRPO w/ VERL.
43.05648.07853.158.122Sep 28, 2025

Evaluation results

MethodLinks
Qwen2.5-7B + GRPO w/ VERL.Base Model=Qwen2.5-7B, Training=GRPO w/ VERL.2025.0962.4
Qwen2.5-7B + PPOBase Model=Qwen2.5-7B, Training=PPO2025.0962.1
Qwen2.5-7B + GRPOBase Model=Qwen2.5-7B, Training=GRPO2025.0961.3
Qwen2.5-7B + PPO w/ VERL.Base Model=Qwen2.5-7B, Training=PPO w/ VERL.2025.0961.3
Qwen2.5-7BBase Model=Qwen2.5-7B2025.0958
Mathstral-7B-v0.1 + GRPO w/ VERL.Base Model=Mathstral-7B-v0.1, Training=GRPO w/ VERL.2025.0951.6
Mathstral-7B-v0.1 + GRPOBase Model=Mathstral-7B-v0.1, Training=GRPO2025.0949.3
Mathstral-7B-v0.1 + PPO w/ VERL.Base Model=Mathstral-7B-v0.1, Training=PPO w/ VERL.2025.0949.1
Mathstral-7B-v0.1 + PPOBase Model=Mathstral-7B-v0.1, Training=PPO2025.0947.5
Mathstral-7B-v0.1Base Model=Mathstral-7B-v0.12025.0943.8