# Multi-robot cooperative Visual Question Answering on CoopSR Habitat Source: [Multi-robot cooperative Visual Question Answering on CoopSR Habitat]() Collection index: [llms.txt]() Data updated: 2026-05-19T13:13:05.772Z Evaluation of model performance on the CoopSR Habitat dataset for Multi-robot cooperative Visual Question Answering, reporting metrics related to cooperation levels (T1-T4, N=2 to N=4) and average performance. 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 Habitat | | Metric | Success Rate (T1) | | 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 - [Success Rate (T1)](): Higher is better; unit: PERCENT. - [Success Rate (T2)](): Higher is better; unit: PERCENT. - [Success Rate (T3)](): Higher is better; unit: PERCENT. - [Success Rate (T4)](): Higher is better; unit: PERCENT. - [Success Rate (N=2)](): Higher is better; unit: PERCENT. - [Success Rate (N=3)](): Higher is better; unit: PERCENT. - [Success Rate (N=4)](): Higher is better; unit: PERCENT. - [Average Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate (T1) | Result date | Report paper | | --- | --- | --- | --- | | SP-CoR | 57.78 | Not recorded | 6a0bef13dbc836b87d82ca9e | | SP-CoR | 57.2 | Not recorded | 6a0bef13dbc836b87d82ca9e | | SP-CoR | 55.36 | Not recorded | 6a0bef13dbc836b87d82ca9e | | EgoRAG | 48.31 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-7B | 46.67 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-72B | 43.96 | Not recorded | 6a0bef13dbc836b87d82ca9e | | TSPO | 42.51 | Not recorded | 6a0bef13dbc836b87d82ca9e | | EgoRAG | 39.9 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoRAG | 39.13 | Not recorded | 6a0bef13dbc836b87d82ca9e | | InternVL3-8B | 39.03 | Not recorded | 6a0bef13dbc836b87d82ca9e | | TSPO | 37.97 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen3-VL-8B-Instruct | 30.53 | Not recorded | 6a0bef13dbc836b87d82ca9e | | LLaVA-NeXT-Video-7B | 26.76 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-7B | 23.96 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-7B-Instruct | 23.57 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoRAG | 22.03 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-2B | 21.26 | Not recorded | 6a0bef13dbc836b87d82ca9e | | LLaVA-NeXT-Video-7B | 20.97 | Not recorded | 6a0bef13dbc836b87d82ca9e | | InternVL3-8B | 20.77 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen3-VL-8B-Instruct | 20.77 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-2B | 20.68 | Not recorded | 6a0bef13dbc836b87d82ca9e | | KTV | 19.71 | Not recorded | 6a0bef13dbc836b87d82ca9e | | VideoLLaMA3-7B | 19.52 | Not recorded | 6a0bef13dbc836b87d82ca9e | | KTV | 19.13 | Not recorded | 6a0bef13dbc836b87d82ca9e | | Qwen2.5-VL-72B-Instruct | 18.84 | Not recorded | 6a0bef13dbc836b87d82ca9e | ### SP-CoR Success Rate (T1): 57.78. Result ID: 6a0c60f4fbc373592c040e7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### SP-CoR Success Rate (T1): 57.2. Result ID: 6a0c60f4fbc373592c040e80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-VL-8B-Instruct"}. This record does not assert independent reproduction. ### SP-CoR Success Rate (T1): 55.36. Result ID: 6a0c60f4fbc373592c040e81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL-7B-Instruct"}. This record does not assert independent reproduction. ### EgoRAG Success Rate (T1): 48.31. Result ID: 6a0c60f4fbc373592c040e79. [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. ### Qwen2.5-VL-7B Success Rate (T1): 46.67. Result ID: 6a0c60f4fbc373592c040e70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B Success Rate (T1): 43.96. Result ID: 6a0c60f4fbc373592c040e71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### TSPO Success Rate (T1): 42.51. Result ID: 6a0c60f4fbc373592c040e7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Keyframe","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### EgoRAG Success Rate (T1): 39.9. Result ID: 6a0c60f4fbc373592c040e7a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"RAG","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### VideoRAG Success Rate (T1): 39.13. Result ID: 6a0c60f4fbc373592c040e77. [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. ### InternVL3-8B Success Rate (T1): 39.03. Result ID: 6a0c60f4fbc373592c040e73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### TSPO Success Rate (T1): 37.97. Result ID: 6a0c60f4fbc373592c040e7b. [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. ### Qwen3-VL-8B-Instruct Success Rate (T1): 30.53. Result ID: 6a0c60f4fbc373592c040e76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### LLaVA-NeXT-Video-7B Success Rate (T1): 26.76. Result ID: 6a0c60f4fbc373592c040e6b. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### VideoLLaMA3-7B Success Rate (T1): 23.96. Result ID: 6a0c60f4fbc373592c040e6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct Success Rate (T1): 23.57. Result ID: 6a0c60f4fbc373592c040e69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### VideoRAG Success Rate (T1): 22.03. Result ID: 6a0c60f4fbc373592c040e78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"RAG","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### VideoLLaMA3-2B Success Rate (T1): 21.26. Result ID: 6a0c60f4fbc373592c040e6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### LLaVA-NeXT-Video-7B Success Rate (T1): 20.97. Result ID: 6a0c60f4fbc373592c040e72. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### InternVL3-8B Success Rate (T1): 20.77. Result ID: 6a0c60f4fbc373592c040e6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct Success Rate (T1): 20.77. Result ID: 6a0c60f4fbc373592c040e6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### VideoLLaMA3-2B Success Rate (T1): 20.68. Result ID: 6a0c60f4fbc373592c040e75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### KTV Success Rate (T1): 19.71. Result ID: 6a0c60f4fbc373592c040e7d. [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. ### VideoLLaMA3-7B Success Rate (T1): 19.52. Result ID: 6a0c60f4fbc373592c040e74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"SFT"}. This record does not assert independent reproduction. ### KTV Success Rate (T1): 19.13. Result ID: 6a0c60f4fbc373592c040e7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Keyframe","Base Model":"InternVL3-8B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B-Instruct Success Rate (T1): 18.84. Result ID: 6a0c60f4fbc373592c040e6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.