# Referring Expression Grounding on Ferret-Bench Source: [Referring Expression Grounding on Ferret-Bench]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:30.925Z Evaluation of model performance on the Referring Expression Grounding task using the Ferret-Bench dataset, typically measured by average 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 | Referring Expression Grounding | | Dataset (including any stated split) | Ferret-Bench | | Metric | Accuracy (avg) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 (avg)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (avg) | Result date | Report paper | | --- | --- | --- | --- | | MM1.5-30B | 77.1 | Not recorded | 68fa75051e209131cea65504 | | Ferret-V2-7B | 75.6 | Not recorded | 68fa75051e209131cea65504 | | Ferret-V2-13B | 74.9 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-7B | 72.6 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-3B-MoE | 72.2 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-1B-MoE | 69.6 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-3B | 69.5 | Not recorded | 68fa75051e209131cea65504 | | MM1.5-1B | 67.4 | Not recorded | 68fa75051e209131cea65504 | | Ferret-13B | 66.3 | Not recorded | 68fa75051e209131cea65504 | | Ferret-7B | 64.5 | Not recorded | 68fa75051e209131cea65504 | | MM1-30B | 50.9 | Not recorded | 68fa75051e209131cea65504 | | MM1-7B | 48.5 | Not recorded | 68fa75051e209131cea65504 | | SPHINX-Tiny | 47.3 | Not recorded | 68fa75051e209131cea65504 | | MM1-3B | 46.3 | Not recorded | 68fa75051e209131cea65504 | | LLaVA-OneVision-7B | 38.4 | Not recorded | 68fa75051e209131cea65504 | | InternVL2 | 35 | Not recorded | 68fa75051e209131cea65504 | | Phi-3-Vision-4B | 32.2 | Not recorded | 68fa75051e209131cea65504 | | MiniCPM-v2-3B | 22.1 | Not recorded | 68fa75051e209131cea65504 | ### MM1.5-30B Accuracy (avg): 77.1. Result ID: 699370673a6c31484915f003. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"Larger (\>13B)"}. This record does not assert independent reproduction. ### Ferret-V2-7B Accuracy (avg): 75.6. Result ID: 699370673a6c31484915effd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction. ### Ferret-V2-13B Accuracy (avg): 74.9. Result ID: 699370673a6c31484915f001. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"Larger (\>13B)"}. This record does not assert independent reproduction. ### MM1.5-7B Accuracy (avg): 72.6. Result ID: 699370673a6c31484915efff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction. ### MM1.5-3B-MoE Accuracy (avg): 72.2. Result ID: 699370673a6c31484915effa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"3B","Architecture":"MoE"}. This record does not assert independent reproduction. ### MM1.5-1B-MoE Accuracy (avg): 69.6. Result ID: 699370673a6c31484915eff4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"1B","Architecture":"MoE"}. This record does not assert independent reproduction. ### MM1.5-3B Accuracy (avg): 69.5. Result ID: 699370673a6c31484915eff9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction. ### MM1.5-1B Accuracy (avg): 67.4. Result ID: 699370673a6c31484915eff3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"1B"}. This record does not assert independent reproduction. ### Ferret-13B Accuracy (avg): 66.3. Result ID: 699370673a6c31484915f000. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"Larger (\>13B)"}. This record does not assert independent reproduction. ### Ferret-7B Accuracy (avg): 64.5. Result ID: 699370673a6c31484915effc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction. ### MM1-30B Accuracy (avg): 50.9. Result ID: 699370673a6c31484915f002. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"Larger (\>13B)"}. This record does not assert independent reproduction. ### MM1-7B Accuracy (avg): 48.5. Result ID: 699370673a6c31484915effe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction. ### SPHINX-Tiny Accuracy (avg): 47.3. Result ID: 699370673a6c31484915eff2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"1B"}. This record does not assert independent reproduction. ### MM1-3B Accuracy (avg): 46.3. Result ID: 699370673a6c31484915eff8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction. ### LLaVA-OneVision-7B Accuracy (avg): 38.4. Result ID: 699370673a6c31484915effb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction. ### InternVL2 Accuracy (avg): 35. Result ID: 699370673a6c31484915eff7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction. ### Phi-3-Vision-4B Accuracy (avg): 32.2. Result ID: 699370673a6c31484915eff6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction. ### MiniCPM-v2-3B Accuracy (avg): 22.1. Result ID: 699370673a6c31484915eff5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.