# Multi-robot cooperative Visual Question Answering on CoopSR iGibson Source: [Multi-robot cooperative Visual Question Answering on CoopSR iGibson]() Collection index: [llms.txt]() Data updated: 2026-05-19T13:13:05.803Z Evaluation of model performance on the CoopSR iGibson dataset for Multi-robot cooperative Visual Question Answering, reporting metrics related to individual robot performance (T1-T4) and cooperative performance across different team sizes (N=2, N=3, N=4). 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-robot cooperative Visual Question Answering | | Dataset (including any stated split) | CoopSR iGibson | | Metric | T1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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 - [T1 Score](): Higher is better; unit: PERCENT. - [T2 Score](): Higher is better; unit: PERCENT. - [T3 Score](): Higher is better; unit: PERCENT. - [T4 Score](): Higher is better; unit: PERCENT. - [Cooperative Performance (N=2)](): Higher is better; unit: PERCENT. - [Cooperative Performance (N=3)](): Higher is better; unit: PERCENT. - [Cooperative Performance (N=4)](): Higher is better; unit: PERCENT. - [Average Cooperative Performance](): Higher is better; unit: PERCENT. ## Recorded results | Method | T1 Score | Result date | Report paper | | --- | --- | --- | --- | | TSPO | 0.8611 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-7B | 0.8 | Not recorded | 6a0bef13dbc836b87d82ca9e | | InternVL3-8B | 0.7944 | Not recorded | 6a0bef13dbc836b87d82ca9e | | TSPO | 0.7944 | Not recorded | 6a0bef13dbc836b87d82ca9e | | SP-CoR | 0.7944 | Not recorded | 6a0bef13dbc836b87d82ca9e | | EgoRAG | 0.7778 | Not recorded | 6a0bef13dbc836b87d82ca9e | | SP-CoR | 0.7611 | Not recorded | 6a0bef13dbc836b87d82ca9e | | SP-CoR | 0.7444 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-72B | 0.7389 | Not recorded | 6a0bef13dbc836b87d82ca9e | | EgoRAG | 0.7222 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoRAG | 0.6778 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen3-VL-8B-Instruct | 0.5944 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-7B-Instruct | 0.3944 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen3-VL-8B-Instruct | 0.3556 | Not recorded | 6a0bef13dbc836b87d82ca9e | | InternVL3-8B | 0.2815 | Not recorded | 6a0bef13dbc836b87d82ca9e | | KTV | 0.2167 | Not recorded | 6a0bef13dbc836b87d82ca9e | | LLaVA-NeXT-Video-7B | 0.2111 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-7B | 0.1944 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-72B-Instruct | 0.1884 | Not recorded | 6a0bef13dbc836b87d82ca9e | | LLaVA-NeXT-Video-7B | 0.1833 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-2B | 0.1556 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-7B | 0.1389 | Not recorded | 6a0bef13dbc836b87d82ca9e | | KTV | 0.1389 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-2B | 0.1278 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoRAG | 0.1222 | Not recorded | 6a0bef13dbc836b87d82ca9e | ### TSPO T1 Score: 0.8611. Result ID: 6a0c60f4fbc373592c040e94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Keyframe","Base Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B T1 Score: 0.8. Result ID: 6a0c60f4fbc373592c040e89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### InternVL3-8B T1 Score: 0.7944. Result ID: 6a0c60f4fbc373592c040e8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### TSPO T1 Score: 0.7944. Result ID: 6a0c60f4fbc373592c040e95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Keyframe","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### SP-CoR T1 Score: 0.7944. Result ID: 6a0c60f4fbc373592c040e99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-VL-8B-Instruct"}. This record does not assert independent reproduction. ### EgoRAG T1 Score: 0.7778. Result ID: 6a0c60f4fbc373592c040e92. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"RAG","Base Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### SP-CoR T1 Score: 0.7611. Result ID: 6a0c60f4fbc373592c040e98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### SP-CoR T1 Score: 0.7444. Result ID: 6a0c60f4fbc373592c040e9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B T1 Score: 0.7389. Result ID: 6a0c60f4fbc373592c040e8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### EgoRAG T1 Score: 0.7222. Result ID: 6a0c60f4fbc373592c040e93. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"RAG","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### VideoRAG T1 Score: 0.6778. Result ID: 6a0c60f4fbc373592c040e90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"RAG","Base Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct T1 Score: 0.5944. Result ID: 6a0c60f4fbc373592c040e8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct T1 Score: 0.3944. Result ID: 6a0c60f4fbc373592c040e82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct T1 Score: 0.3556. Result ID: 6a0c60f4fbc373592c040e88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### InternVL3-8B T1 Score: 0.2815. Result ID: 6a0c60f4fbc373592c040e85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### KTV T1 Score: 0.2167. Result ID: 6a0c60f4fbc373592c040e96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Keyframe","Base Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### LLaVA-NeXT-Video-7B T1 Score: 0.2111. Result ID: 6a0c60f4fbc373592c040e84. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### VideoLLaMA3-7B T1 Score: 0.1944. Result ID: 6a0c60f4fbc373592c040e86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B-Instruct T1 Score: 0.1884. Result ID: 6a0c60f4fbc373592c040e83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### LLaVA-NeXT-Video-7B T1 Score: 0.1833. Result ID: 6a0c60f4fbc373592c040e8b. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### VideoLLaMA3-2B T1 Score: 0.1556. Result ID: 6a0c60f4fbc373592c040e8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### VideoLLaMA3-7B T1 Score: 0.1389. Result ID: 6a0c60f4fbc373592c040e8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### KTV T1 Score: 0.1389. Result ID: 6a0c60f4fbc373592c040e97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Keyframe","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### VideoLLaMA3-2B T1 Score: 0.1278. Result ID: 6a0c60f4fbc373592c040e87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### VideoRAG T1 Score: 0.1222. Result ID: 6a0c60f4fbc373592c040e91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"RAG","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.