# Multi-modal Understanding on MM-Vet v1 (full) Source: [Multi-modal Understanding on MM-Vet v1 (full)]() Collection index: [llms.txt]() Data updated: 2026-05-25T07:07:05.174Z Evaluation of model performance on the full set of the MM-Vet v1 benchmark, covering sub-tasks including Recognition (Rec), OCR, Knowledge (Know), Generation (Gen), Spatial reasoning (Spat), and Math. 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 | Multi-modal Understanding | | Dataset (including any stated split) | MM-Vet v1 (full) | | Metric | Overall Score (MM-Vet v1) | | 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 - [Overall Score (MM-Vet v1)](): Higher is better; unit: PERCENT. - [Recognition Score](): Higher is better; unit: PERCENT. - [OCR Score](): Higher is better; unit: PERCENT. - [Knowledge Score](): Higher is better; unit: PERCENT. - [Generation Score](): Higher is better; unit: PERCENT. - [Spatial Reasoning Score](): Higher is better; unit: PERCENT. - [Math Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Score (MM-Vet v1) | Result date | Report paper | | --- | --- | --- | --- | | Ours | 36.2 | Not recorded | 68fa7a321e209131cea81adb | | LLaVA-v1.5-13B | 36 | Not recorded | 68fa7a321e209131cea81adb | | vanilla-DPO | 35 | Not recorded | 68fa7a321e209131cea81adb | | VCD | 33.7 | Not recorded | 68fa7a321e209131cea81adb | | HSA-DPO | 33.7 | Not recorded | 68fa7a321e209131cea81adb | | Ours + HA-DPO | 33.5 | Not recorded | 68fa7a321e209131cea81adb | | Ours | 32.6 | Not recorded | 68fa7a321e209131cea81adb | | POVID | 31.8 | Not recorded | 68fa7a321e209131cea81adb | | EFUF | 31.2 | Not recorded | 68fa7a321e209131cea81adb | | LLaVA-v1.5-7B | 31 | Not recorded | 68fa7a321e209131cea81adb | | DoLa | 30.8 | Not recorded | 68fa7a321e209131cea81adb | | HA-DPO | 30.6 | Not recorded | 68fa7a321e209131cea81adb | | OPERA | 30.3 | Not recorded | 68fa7a321e209131cea81adb | | RLAIF-V | 29.9 | Not recorded | 68fa7a321e209131cea81adb | | VCD | 29.8 | Not recorded | 68fa7a321e209131cea81adb | | TPO | 25.7 | Not recorded | 68fa7a321e209131cea81adb | ### Ours Overall Score (MM-Vet v1): 36.2. Result ID: 6a13f49cfbc373592c0aa030. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction. ### LLaVA-v1.5-13B Overall Score (MM-Vet v1): 36. Result ID: 6a13f49cfbc373592c0aa02c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction. ### vanilla-DPO Overall Score (MM-Vet v1): 35. Result ID: 6a13f49cfbc373592c0aa02e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction. ### VCD Overall Score (MM-Vet v1): 33.7. Result ID: 6a13f49cfbc373592c0aa02d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction. ### HSA-DPO Overall Score (MM-Vet v1): 33.7. Result ID: 6a13f49cfbc373592c0aa02f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"13B"}. This record does not assert independent reproduction. ### Ours + HA-DPO Overall Score (MM-Vet v1): 33.5. Result ID: 6a13f49cfbc373592c0aa02b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Ours Overall Score (MM-Vet v1): 32.6. Result ID: 6a13f49cfbc373592c0aa02a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### POVID Overall Score (MM-Vet v1): 31.8. Result ID: 6a13f49cfbc373592c0aa027. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### EFUF Overall Score (MM-Vet v1): 31.2. Result ID: 6a13f49cfbc373592c0aa025. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### LLaVA-v1.5-7B Overall Score (MM-Vet v1): 31. Result ID: 6a13f49cfbc373592c0aa021. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### DoLa Overall Score (MM-Vet v1): 30.8. Result ID: 6a13f49cfbc373592c0aa024. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### HA-DPO Overall Score (MM-Vet v1): 30.6. Result ID: 6a13f49cfbc373592c0aa026. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### OPERA Overall Score (MM-Vet v1): 30.3. Result ID: 6a13f49cfbc373592c0aa023. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### RLAIF-V Overall Score (MM-Vet v1): 29.9. Result ID: 6a13f49cfbc373592c0aa028. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### VCD Overall Score (MM-Vet v1): 29.8. Result ID: 6a13f49cfbc373592c0aa022. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### TPO Overall Score (MM-Vet v1): 25.7. Result ID: 6a13f49cfbc373592c0aa029. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.