List your company

Astronomy Question Answering on AstroQA English

61.2Pass@1Qwen2.5-7B
50.2853.11555.9558.785Sep 28, 2025

Evaluation results

MethodLinks
Qwen2.5-7BBase Model=Qwen2.5-7B2025.0961.2
Qwen2.5-7B + PPO w/ VERL.Base Model=Qwen2.5-7B, Training=PPO w/ VERL.2025.0960.9
Qwen2.5-7B + PPOBase Model=Qwen2.5-7B, Training=PPO2025.0960
Qwen2.5-7B + GRPOBase Model=Qwen2.5-7B, Training=GRPO2025.0959.6
Qwen2.5-7B + GRPO w/ VERL.Base Model=Qwen2.5-7B, Training=GRPO w/ VERL.2025.0959.4
Mathstral-7B-v0.1 + GRPO w/ VERL.Base Model=Mathstral-7B-v0.1, Training=GRPO w/ VERL.2025.0958
Mathstral-7B-v0.1 + GRPOBase Model=Mathstral-7B-v0.1, Training=GRPO2025.0957.1
Mathstral-7B-v0.1 + PPO w/ VERL.Base Model=Mathstral-7B-v0.1, Training=PPO w/ VERL.2025.0954.5
Mathstral-7B-v0.1 + PPOBase Model=Mathstral-7B-v0.1, Training=PPO2025.0952.7
Mathstral-7B-v0.1Base Model=Mathstral-7B-v0.12025.0950.7