# Multi-modal Instruction Following on LLaVA-Wild Source: [Multi-modal Instruction Following on LLaVA-Wild]() Collection index: [llms.txt]() Data updated: 2026-03-04T13:29:44.239Z Evaluation of model performance on following multi-modal instructions using the LLaVA-Wild dataset, measured by the Average score. 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 Instruction Following | | Dataset (including any stated split) | LLaVA-Wild | | Metric | Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | VisNec | 69.8 | Not recorded | 69a66c162d603e6de3e3ce08 | | Full-Data(665K) | 67.9 | Not recorded | 69a66c162d603e6de3e3ce08 | | CNS | 66.84 | Not recorded | 6981810aa8b01e76cc8e2267 | | CoIDO | 66.7 | Not recorded | 69a66c162d603e6de3e3ce08 | | CNS | 65.92 | Not recorded | 6981810aa8b01e76cc8e2267 | | PreSel | 65.6 | Not recorded | 69a66c162d603e6de3e3ce08 | | ICONS | 65.3 | Not recorded | 69a66c162d603e6de3e3ce08 | | TypiClust | 65.2 | Not recorded | 69a66c162d603e6de3e3ce08 | | COINCIDE | 64.9 | Not recorded | 69a66c162d603e6de3e3ce08 | | Vanilla | 64.8 | Not recorded | 6981810aa8b01e76cc8e2267 | | VCD | 63.28 | Not recorded | 6981810aa8b01e76cc8e2267 | | XMAS | 62.4 | Not recorded | 69a66c162d603e6de3e3ce08 | | IFD | 62.3 | Not recorded | 69a66c162d603e6de3e3ce08 | | CLIP-Score | 61.3 | Not recorded | 69a66c162d603e6de3e3ce08 | | Self-Filter | 60.6 | Not recorded | 69a66c162d603e6de3e3ce08 | | EL2N | 59 | Not recorded | 69a66c162d603e6de3e3ce08 | | Random | 58.8 | Not recorded | 69a66c162d603e6de3e3ce08 | ### VisNec Average Score: 69.8. Result ID: 69a833af6dbb7075b94eb21b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### Full-Data(665K) Average Score: 67.9. Result ID: 69a833af6dbb7075b94eb20f. [Reporting paper]() Recorded evaluation configuration: {"Sampling Ratio":"100% (665K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### CNS Average Score: 66.84. Result ID: 699769bd5698665ec4bd4656. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_method":"VCD"}. This record does not assert independent reproduction. ### CoIDO Average Score: 66.7. Result ID: 69a833af6dbb7075b94eb219. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### CNS Average Score: 65.92. Result ID: 699769bd5698665ec4bd4654. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_method":"Vanilla"}. This record does not assert independent reproduction. ### PreSel Average Score: 65.6. Result ID: 69a833af6dbb7075b94eb215. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### ICONS Average Score: 65.3. Result ID: 69a833af6dbb7075b94eb21a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### TypiClust Average Score: 65.2. Result ID: 69a833af6dbb7075b94eb213. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### COINCIDE Average Score: 64.9. Result ID: 69a833af6dbb7075b94eb217. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### Vanilla Average Score: 64.8. Result ID: 699769bd5698665ec4bd4653. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VCD Average Score: 63.28. Result ID: 699769bd5698665ec4bd4655. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### XMAS Average Score: 62.4. Result ID: 69a833af6dbb7075b94eb216. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### IFD Average Score: 62.3. Result ID: 69a833af6dbb7075b94eb214. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### CLIP-Score Average Score: 61.3. Result ID: 69a833af6dbb7075b94eb218. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### Self-Filter Average Score: 60.6. Result ID: 69a833af6dbb7075b94eb211. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### EL2N Average Score: 59. Result ID: 69a833af6dbb7075b94eb212. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. ### Random Average Score: 58.8. Result ID: 69a833af6dbb7075b94eb210. [Reporting paper]() Recorded evaluation configuration: {"Sampling Ratio":"15% (98K samples)","Base Model":"LLaVA-v1.5-7B","Training Dataset":"LLaVA-665K"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.