# Astronomy Question Answering on AstroQA Chinese Source: [Astronomy Question Answering on AstroQA Chinese]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:30:54.179Z Evaluation of model performance on the AstroQA Chinese dataset for Astronomy Question Answering tasks, measured using Pass@1. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Astronomy Question Answering | | Dataset (including any stated split) | AstroQA Chinese | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Pass@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-7B + GRPO w/ VERL. | 62.4 | Not recorded | 68fa7bc11e209131cea8a35b | | Qwen2.5-7B + PPO | 62.1 | Not recorded | 68fa7bc11e209131cea8a35b | | Qwen2.5-7B + GRPO | 61.3 | Not recorded | 68fa7bc11e209131cea8a35b | | Qwen2.5-7B + PPO w/ VERL. | 61.3 | Not recorded | 68fa7bc11e209131cea8a35b | | Qwen2.5-7B | 58 | Not recorded | 68fa7bc11e209131cea8a35b | | Mathstral-7B-v0.1 + GRPO w/ VERL. | 51.6 | Not recorded | 68fa7bc11e209131cea8a35b | | Mathstral-7B-v0.1 + GRPO | 49.3 | Not recorded | 68fa7bc11e209131cea8a35b | | Mathstral-7B-v0.1 + PPO w/ VERL. | 49.1 | Not recorded | 68fa7bc11e209131cea8a35b | | Mathstral-7B-v0.1 + PPO | 47.5 | Not recorded | 68fa7bc11e209131cea8a35b | | Mathstral-7B-v0.1 | 43.8 | Not recorded | 68fa7bc11e209131cea8a35b | ### Qwen2.5-7B + GRPO w/ VERL. Pass@1: 62.4. Result ID: 69ddfb2047f34ce924c56248. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B","Training":"GRPO w/ VERL."}. This record does not assert independent reproduction. ### Qwen2.5-7B + PPO Pass@1: 62.1. Result ID: 69ddfb2047f34ce924c56249. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B","Training":"PPO"}. This record does not assert independent reproduction. ### Qwen2.5-7B + GRPO Pass@1: 61.3. Result ID: 69ddfb2047f34ce924c56247. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B","Training":"GRPO"}. This record does not assert independent reproduction. ### Qwen2.5-7B + PPO w/ VERL. Pass@1: 61.3. Result ID: 69ddfb2047f34ce924c5624a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B","Training":"PPO w/ VERL."}. This record does not assert independent reproduction. ### Qwen2.5-7B Pass@1: 58. Result ID: 69ddfb2047f34ce924c56246. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### Mathstral-7B-v0.1 + GRPO w/ VERL. Pass@1: 51.6. Result ID: 69ddfb2047f34ce924c56243. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Mathstral-7B-v0.1","Training":"GRPO w/ VERL."}. This record does not assert independent reproduction. ### Mathstral-7B-v0.1 + GRPO Pass@1: 49.3. Result ID: 69ddfb2047f34ce924c56242. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Mathstral-7B-v0.1","Training":"GRPO"}. This record does not assert independent reproduction. ### Mathstral-7B-v0.1 + PPO w/ VERL. Pass@1: 49.1. Result ID: 69ddfb2047f34ce924c56245. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Mathstral-7B-v0.1","Training":"PPO w/ VERL."}. This record does not assert independent reproduction. ### Mathstral-7B-v0.1 + PPO Pass@1: 47.5. Result ID: 69ddfb2047f34ce924c56244. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Mathstral-7B-v0.1","Training":"PPO"}. This record does not assert independent reproduction. ### Mathstral-7B-v0.1 Pass@1: 43.8. Result ID: 69ddfb2047f34ce924c56241. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Mathstral-7B-v0.1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.