# Vision-Language Modeling on VisP Source: [Vision-Language Modeling on VisP]() Collection index: [llms.txt]() Data updated: 2026-06-17T08:11:51.856Z Evaluation of model performance on the VisP dataset for Vision-Language Modeling tasks, measured using 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) | VisP | | 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 | 42 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 40.3 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 39.2 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 38.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 38.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 38.4 | Not recorded | 6a322a62d33dfb23e783ee2d | | Qwen3.5 | 38.3 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 37.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | ZPPO | 35 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 27.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | GRPO | 24.2 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 21.2 | Not recorded | 6a322a62d33dfb23e783ee2d | | On-Distill | 20.9 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 20.8 | Not recorded | 6a322a62d33dfb23e783ee2d | | Qwen3.5 | 20.5 | Not recorded | 6a322a62d33dfb23e783ee2d | | Off-Distill | 20 | Not recorded | 6a322a62d33dfb23e783ee2d | ### ZPPO Accuracy: 42. Result ID: 6a3255a6fbc373592c2fc2a3. [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: 40.3. Result ID: 6a3255a6fbc373592c2fc2a2. [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: 39.2. Result ID: 6a3255a6fbc373592c2fc2a1. [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: 38.8. Result ID: 6a3255a6fbc373592c2fc29f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### On-Distill Accuracy: 38.8. Result ID: 6a3255a6fbc373592c2fc2a0. [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: 38.4. Result ID: 6a3255a6fbc373592c2fc29d. [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: 38.3. Result ID: 6a3255a6fbc373592c2fc29c. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### Off-Distill Accuracy: 37.8. Result ID: 6a3255a6fbc373592c2fc29e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### ZPPO Accuracy: 35. Result ID: 6a3255a6fbc373592c2fc29b. [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: 27.8. Result ID: 6a3255a6fbc373592c2fc29a. [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: 24.2. Result ID: 6a3255a6fbc373592c2fc299. [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: 21.2. Result ID: 6a3255a6fbc373592c2fc297. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### On-Distill Accuracy: 20.9. Result ID: 6a3255a6fbc373592c2fc298. [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: 20.8. Result ID: 6a3255a6fbc373592c2fc296. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":true}. This record does not assert independent reproduction. ### Qwen3.5 Accuracy: 20.5. Result ID: 6a3255a6fbc373592c2fc294. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"0.8B","Prompt Replay Buffer Augmentation":false}. This record does not assert independent reproduction. ### Off-Distill Accuracy: 20. Result ID: 6a3255a6fbc373592c2fc295. [Reporting paper]() [Method origin 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.