Astronomy Question Answering on AstroQA Chinese
62.4Pass@1Qwen2.5-7B + GRPO w/ VERL.
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-7B + GRPO w/ VERL.Base Model=Qwen2.5-7B, Training=GRPO w/ VERL.2025.09 | 62.4 | |
| Qwen2.5-7B + PPOBase Model=Qwen2.5-7B, Training=PPO2025.09 | 62.1 | |
| Qwen2.5-7B + GRPOBase Model=Qwen2.5-7B, Training=GRPO2025.09 | 61.3 | |
| Qwen2.5-7B + PPO w/ VERL.Base Model=Qwen2.5-7B, Training=PPO w/ VERL.2025.09 | 61.3 | |
| Qwen2.5-7BBase Model=Qwen2.5-7B2025.09 | 58 | |
| Mathstral-7B-v0.1 + GRPO w/ VERL.Base Model=Mathstral-7B-v0.1, Training=GRPO w/ VERL.2025.09 | 51.6 | |
| Mathstral-7B-v0.1 + GRPOBase Model=Mathstral-7B-v0.1, Training=GRPO2025.09 | 49.3 | |
| Mathstral-7B-v0.1 + PPO w/ VERL.Base Model=Mathstral-7B-v0.1, Training=PPO w/ VERL.2025.09 | 49.1 | |
| Mathstral-7B-v0.1 + PPOBase Model=Mathstral-7B-v0.1, Training=PPO2025.09 | 47.5 | |
| Mathstral-7B-v0.1Base Model=Mathstral-7B-v0.12025.09 | 43.8 |