# Video Spatial Understanding on MMSI-Bench 500 QA 1.0 Source: [Video Spatial Understanding on MMSI-Bench 500 QA 1.0]() Collection index: [llms.txt]() Data updated: 2026-06-11T09:56:17.071Z Evaluation of model performance on the MMSI-Bench 500 QA 1.0 dataset focusing on Video Spatial Understanding capabilities, measured by 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 | Video Spatial Understanding | | Dataset (including any stated split) | MMSI-Bench 500 QA 1.0 | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CoCoSI | 41 | Not recorded | 6a28f32090966ade919c1637 | | CoCoSI | 39.1 | Not recorded | 6a28f32090966ade919c1637 | | Single-Agent Baseline | 36.6 | Not recorded | 6a28f32090966ade919c1637 | | TraveLER | 36 | Not recorded | 6a28f32090966ade919c1637 | | VCA | 35.8 | Not recorded | 6a28f32090966ade919c1637 | | VideoAgent | 35.4 | Not recorded | 6a28f32090966ade919c1637 | | CoCoSI | 35.3 | Not recorded | 6a28f32090966ade919c1637 | | Single-Agent Baseline | 35 | Not recorded | 6a28f32090966ade919c1637 | | TraveLER | 34.7 | Not recorded | 6a28f32090966ade919c1637 | | VCA | 34.2 | Not recorded | 6a28f32090966ade919c1637 | | VideoAgent | 33.8 | Not recorded | 6a28f32090966ade919c1637 | | Single-Agent Baseline | 32.4 | Not recorded | 6a28f32090966ade919c1637 | | TraveLER | 31.9 | Not recorded | 6a28f32090966ade919c1637 | | VCA | 31.6 | Not recorded | 6a28f32090966ade919c1637 | | VideoAgent | 31.2 | Not recorded | 6a28f32090966ade919c1637 | ### CoCoSI Accuracy: 41. Result ID: 6a2a8495fbc373592c281d2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Gemini-based","Training-free":"true","Agentic Collaboration":"true","CogMap":"true"}. This record does not assert independent reproduction. ### CoCoSI Accuracy: 39.1. Result ID: 6a2a8495fbc373592c281d25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-based","Training-free":"true","Agentic Collaboration":"true","CogMap":"true"}. This record does not assert independent reproduction. ### Single-Agent Baseline Accuracy: 36.6. Result ID: 6a2a8495fbc373592c281d26. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Gemini-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"true"}. This record does not assert independent reproduction. ### TraveLER Accuracy: 36. Result ID: 6a2a8495fbc373592c281d27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Gemini-based","Training-free":"true","Agentic Collaboration":"true","CogMap":"false"}. This record does not assert independent reproduction. ### VCA Accuracy: 35.8. Result ID: 6a2a8495fbc373592c281d29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Gemini-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"false"}. This record does not assert independent reproduction. ### VideoAgent Accuracy: 35.4. Result ID: 6a2a8495fbc373592c281d28. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"false"}. This record does not assert independent reproduction. ### CoCoSI Accuracy: 35.3. Result ID: 6a2a8495fbc373592c281d2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-VL-based","Training-free":"true","Agentic Collaboration":"true","CogMap":"true"}. This record does not assert independent reproduction. ### Single-Agent Baseline Accuracy: 35. Result ID: 6a2a8495fbc373592c281d21. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"true"}. This record does not assert independent reproduction. ### TraveLER Accuracy: 34.7. Result ID: 6a2a8495fbc373592c281d22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-based","Training-free":"true","Agentic Collaboration":"true","CogMap":"false"}. This record does not assert independent reproduction. ### VCA Accuracy: 34.2. Result ID: 6a2a8495fbc373592c281d24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"false"}. This record does not assert independent reproduction. ### VideoAgent Accuracy: 33.8. Result ID: 6a2a8495fbc373592c281d23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"false"}. This record does not assert independent reproduction. ### Single-Agent Baseline Accuracy: 32.4. Result ID: 6a2a8495fbc373592c281d2b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-VL-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"true"}. This record does not assert independent reproduction. ### TraveLER Accuracy: 31.9. Result ID: 6a2a8495fbc373592c281d2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-VL-based","Training-free":"true","Agentic Collaboration":"true","CogMap":"false"}. This record does not assert independent reproduction. ### VCA Accuracy: 31.6. Result ID: 6a2a8495fbc373592c281d2e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-VL-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"false"}. This record does not assert independent reproduction. ### VideoAgent Accuracy: 31.2. Result ID: 6a2a8495fbc373592c281d2d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen-VL-based","Training-free":"true","Agentic Collaboration":"false","CogMap":"false"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.