# Utility Evaluation on LLaVA-Bench Coco Source: [Utility Evaluation on LLaVA-Bench Coco]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:03:46.388Z Evaluation of model utility using the LLaVA-Bench Coco subset. 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 | Utility Evaluation | | Dataset (including any stated split) | LLaVA-Bench Coco | | Metric | Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | ShareGPT4V | 92.3 | Not recorded | 68fa75361e209131cea6676a | | CMRM\_sample | 91.4 | Not recorded | 68fa75361e209131cea6676a | | CMRM\_dataset | 90.5 | Not recorded | 68fa75361e209131cea6676a | | VLGuard Mixed | 90.4 | Not recorded | 68fa75361e209131cea6676a | | CMRM\_dataset | 90.1 | Not recorded | 68fa75361e209131cea6676a | | LLaVA-v1.5-13B | 89.7 | Not recorded | 68fa75361e209131cea6676a | | CMRM\_sample | 89.6 | Not recorded | 68fa75361e209131cea6676a | | VLGuard PH | 88.1 | Not recorded | 68fa75361e209131cea6676a | | VLGuard Mixed | 87.8 | Not recorded | 68fa75361e209131cea6676a | | VLGuard PH | 87.5 | Not recorded | 68fa75361e209131cea6676a | | LLaVA-v1.5-7B | 79.2 | Not recorded | 68fa75361e209131cea6676a | | CMRM\_dataset | 78.7 | Not recorded | 68fa75361e209131cea6676a | | CMRM\_sample | 77.3 | Not recorded | 68fa75361e209131cea6676a | ### ShareGPT4V Score: 92.3. Result ID: 69937a293a6c314849163837. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CMRM\_sample Score: 91.4. Result ID: 69937a293a6c314849163839. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ShareGPT4V"}. This record does not assert independent reproduction. ### CMRM\_dataset Score: 90.5. Result ID: 69937a293a6c314849163835. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-13B"}. This record does not assert independent reproduction. ### VLGuard Mixed Score: 90.4. Result ID: 69937a293a6c314849163833. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-13B"}. This record does not assert independent reproduction. ### CMRM\_dataset Score: 90.1. Result ID: 69937a293a6c314849163838. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ShareGPT4V"}. This record does not assert independent reproduction. ### LLaVA-v1.5-13B Score: 89.7. Result ID: 69937a293a6c314849163832. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CMRM\_sample Score: 89.6. Result ID: 69937a293a6c314849163836. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-13B"}. This record does not assert independent reproduction. ### VLGuard PH Score: 88.1. Result ID: 69937a293a6c31484916382f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-7B"}. This record does not assert independent reproduction. ### VLGuard Mixed Score: 87.8. Result ID: 69937a293a6c31484916382e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-7B"}. This record does not assert independent reproduction. ### VLGuard PH Score: 87.5. Result ID: 69937a293a6c314849163834. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-13B"}. This record does not assert independent reproduction. ### LLaVA-v1.5-7B Score: 79.2. Result ID: 69937a293a6c31484916382d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CMRM\_dataset Score: 78.7. Result ID: 69937a293a6c314849163830. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-7B"}. This record does not assert independent reproduction. ### CMRM\_sample Score: 77.3. Result ID: 69937a293a6c314849163831. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.