# General-purpose Visual Instruction Following on LLaVA-Bench in-the-wild Source: [General-purpose Visual Instruction Following on LLaVA-Bench in-the-wild]() Collection index: [llms.txt]() Data updated: 2026-05-13T08:54:00.888Z Evaluation of model performance on the LLaVA-Bench in-the-wild dataset for general-purpose visual instruction following, reporting scores across specific categories (All\_1, All\_2, All\_3) and an overall average. 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-purpose Visual Instruction Following | | Dataset (including any stated split) | LLaVA-Bench in-the-wild | | Metric | Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Average Score](): Higher is better; unit: PERCENT. - [Score (All\_1)](): Higher is better; unit: PERCENT. - [Score (All\_2)](): Higher is better; unit: PERCENT. - [Score (All\_3)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | LaSCD | 49.3 | Not recorded | 6a0405bfdbc836b87d827743 | | GLM-4V | 49.1 | Not recorded | 6a0405bfdbc836b87d827743 | | DeCo | 48.3 | Not recorded | 6a0405bfdbc836b87d827743 | | LaSCD | 45.9 | Not recorded | 6a0405bfdbc836b87d827743 | | DeCo | 45.6 | Not recorded | 6a0405bfdbc836b87d827743 | | LLaVA-1.5 | 45.1 | Not recorded | 6a0405bfdbc836b87d827743 | | LaSCD | 44.9 | Not recorded | 6a0405bfdbc836b87d827743 | | DeCo | 44.7 | Not recorded | 6a0405bfdbc836b87d827743 | | Qwen-VL | 44.5 | Not recorded | 6a0405bfdbc836b87d827743 | ### LaSCD Average Score: 49.3. Result ID: 6a043b1747f34ce924ea321a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"GLM-4V"}. This record does not assert independent reproduction. ### GLM-4V Average Score: 49.1. Result ID: 6a043b1747f34ce924ea3218. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"GLM-4V"}. This record does not assert independent reproduction. ### DeCo Average Score: 48.3. Result ID: 6a043b1747f34ce924ea3219. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"GLM-4V"}. This record does not assert independent reproduction. ### LaSCD Average Score: 45.9. Result ID: 6a043b1747f34ce924ea3214. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### DeCo Average Score: 45.6. Result ID: 6a043b1747f34ce924ea3213. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### LLaVA-1.5 Average Score: 45.1. Result ID: 6a043b1747f34ce924ea3212. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction. ### LaSCD Average Score: 44.9. Result ID: 6a043b1747f34ce924ea3217. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen-VL"}. This record does not assert independent reproduction. ### DeCo Average Score: 44.7. Result ID: 6a043b1747f34ce924ea3216. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen-VL"}. This record does not assert independent reproduction. ### Qwen-VL Average Score: 44.5. Result ID: 6a043b1747f34ce924ea3215. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Qwen-VL"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.