# General Reasoning & Understanding on MMStar (Accuracy) Source: [General Reasoning & Understanding on MMStar (Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-05-14T06:52:56.588Z Evaluation of model performance on the MMStar dataset for General Reasoning and Understanding tasks, measured by Accuracy. 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 | General Reasoning & Understanding | | Dataset (including any stated split) | MMStar | | Metric | Accuracy (MMStar General Reasoning) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Accuracy (MMStar General Reasoning)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (MMStar General Reasoning) | Result date | Report paper | | --- | --- | --- | --- | | V-STAR | 66.8 | Not recorded | 69ddca347d0172140ec79b45 | | VL-Cogito | 65.3 | Not recorded | 69ddca347d0172140ec79b45 | | ThinkLite-VL | 65 | Not recorded | 69ddca347d0172140ec79b45 | | Qwen3-VL-8B | 64.6 | Not recorded | 6a055710dbc836b87d828c4c | | S^3-FT | 64.1 | Not recorded | 6a055710dbc836b87d828c4c | | S^3-FT | 63.7 | Not recorded | 6a055710dbc836b87d828c4c | | VL-Rethinker | 63 | Not recorded | 69ddca347d0172140ec79b45 | | Qwen2.5VL | 61.7 | Not recorded | 69ddca347d0172140ec79b45 | | S^3-FT | 61.2 | Not recorded | 6a055710dbc836b87d828c4c | | OpenVLThinker | 60.7 | Not recorded | 69ddca347d0172140ec79b45 | | S^3-FT | 60.6 | Not recorded | 6a055710dbc836b87d828c4c | | Qwen2.5-VL-7B | 59.7 | Not recorded | 6a055710dbc836b87d828c4c | | R1-Onevision | 56.2 | Not recorded | 69ddca347d0172140ec79b45 | | Vision-R1 | 56 | Not recorded | 69ddca347d0172140ec79b45 | ### V-STAR Accuracy (MMStar General Reasoning): 66.8. Result ID: 69ddff8147f34ce924c580e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Size":"40k"}. This record does not assert independent reproduction. ### VL-Cogito Accuracy (MMStar General Reasoning): 65.3. Result ID: 69ddff8147f34ce924c580e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Size":"80k"}. This record does not assert independent reproduction. ### ThinkLite-VL Accuracy (MMStar General Reasoning): 65. Result ID: 69ddff8147f34ce924c580e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Size":"11k"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Accuracy (MMStar General Reasoning): 64.6. Result ID: 6a05714347f34ce924ebdadb. [Reporting paper]() Recorded evaluation configuration: {"Mode":"base"}. This record does not assert independent reproduction. ### S^3-FT Accuracy (MMStar General Reasoning): 64.1. Result ID: 6a05714347f34ce924ebdadc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B","Mode":"Single-view"}. This record does not assert independent reproduction. ### S^3-FT Accuracy (MMStar General Reasoning): 63.7. Result ID: 6a05714347f34ce924ebdadd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B","Mode":"Cross-viewpoint"}. This record does not assert independent reproduction. ### VL-Rethinker Accuracy (MMStar General Reasoning): 63. Result ID: 69ddff8147f34ce924c580e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Size":"39k"}. This record does not assert independent reproduction. ### Qwen2.5VL Accuracy (MMStar General Reasoning): 61.7. Result ID: 69ddff8147f34ce924c580dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### S^3-FT Accuracy (MMStar General Reasoning): 61.2. Result ID: 6a05714347f34ce924ebdadf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B","Mode":"Single-view"}. This record does not assert independent reproduction. ### OpenVLThinker Accuracy (MMStar General Reasoning): 60.7. Result ID: 69ddff8147f34ce924c580e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Size":"59.2k"}. This record does not assert independent reproduction. ### S^3-FT Accuracy (MMStar General Reasoning): 60.6. Result ID: 6a05714347f34ce924ebdae0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B","Mode":"Cross-viewpoint"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy (MMStar General Reasoning): 59.7. Result ID: 6a05714347f34ce924ebdade. [Reporting paper]() Recorded evaluation configuration: {"Mode":"base"}. This record does not assert independent reproduction. ### R1-Onevision Accuracy (MMStar General Reasoning): 56.2. Result ID: 69ddff8147f34ce924c580de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Size":"155k"}. This record does not assert independent reproduction. ### Vision-R1 Accuracy (MMStar General Reasoning): 56. Result ID: 69ddff8147f34ce924c580df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Size":"210k"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.