# Vision-Language Modeling on MVerse Source: [Vision-Language Modeling on MVerse]() Collection index: [llms.txt]() Data updated: 2026-06-17T08:11:51.644Z Evaluation of Vision-Language Modeling performance on the MVerse dataset, typically 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 | Vision-Language Modeling | | Dataset (including any stated split) | MVerse | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ZPPO | 76 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 72.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 72.3 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 72 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 71.9 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 71.4 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 70.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | Qwen3.5 | 69.7 | Not recorded | 6a322a62d33dfb23e783ee2d | | ZPPO | 59.3 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 51.1 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 47.7 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 47.4 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 45.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 45.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 45.3 | Not recorded | 6a322a62d33dfb23e783ee2d | | Qwen3.5 | 43.5 | Not recorded | 6a322a62d33dfb23e783ee2d | ### ZPPO Accuracy: 76. Result ID: 6a3255a6fbc373592c2fc233. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### GRPO Accuracy: 72.8. Result ID: 6a3255a6fbc373592c2fc232. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### GRPO Accuracy: 72.3. Result ID: 6a3255a6fbc373592c2fc231. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### On-Distill Accuracy: 72. Result ID: 6a3255a6fbc373592c2fc230. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### On-Distill Accuracy: 71.9. Result ID: 6a3255a6fbc373592c2fc22f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### Off-Distill Accuracy: 71.4. Result ID: 6a3255a6fbc373592c2fc22e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### Off-Distill Accuracy: 70.8. Result ID: 6a3255a6fbc373592c2fc22d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### Qwen3.5 Accuracy: 69.7. Result ID: 6a3255a6fbc373592c2fc22c. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### ZPPO Accuracy: 59.3. Result ID: 6a3255a6fbc373592c2fc22b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### GRPO Accuracy: 51.1. Result ID: 6a3255a6fbc373592c2fc22a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### GRPO Accuracy: 47.7. Result ID: 6a3255a6fbc373592c2fc229. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### On-Distill Accuracy: 47.4. Result ID: 6a3255a6fbc373592c2fc228. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### Off-Distill Accuracy: 45.8. Result ID: 6a3255a6fbc373592c2fc226. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### On-Distill Accuracy: 45.8. Result ID: 6a3255a6fbc373592c2fc227. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### Off-Distill Accuracy: 45.3. Result ID: 6a3255a6fbc373592c2fc225. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### Qwen3.5 Accuracy: 43.5. Result ID: 6a3255a6fbc373592c2fc224. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.