# Robotic Video Question Answering on RoboVQA (test) Source: [Robotic Video Question Answering on RoboVQA (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:37:14.368Z Evaluation of model performance on the test split of the RoboVQA dataset for Robotic Video Question Answering, measured using a suite of BLEU scores including BLEU-avg. 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 | Robotic Video Question Answering | | Dataset (including any stated split) | RoboVQA (test) | | Metric | BLEU-1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [BLEU-1](): Higher is better; unit: PERCENT. - [BLEU-2](): Higher is better; unit: PERCENT. - [BLEU-3](): Higher is better; unit: PERCENT. - [BLEU-4](): Higher is better; unit: PERCENT. - [BLEU-avg](): Higher is better; unit: PERCENT. ## Recorded results | Method | BLEU-1 | Result date | Report paper | | --- | --- | --- | --- | | Thinker-7B | 72.7 | Not recorded | 697c3af0a8b01e76cc8da39a | | RoboBrain-7B | 72.05 | Not recorded | 697c3af0a8b01e76cc8da39a | | ThinkAct-7B | 69.1 | Not recorded | 697c3af0a8b01e76cc8da39a | | Qwen2.5-VL-7B | 62.2 | Not recorded | 697c3af0a8b01e76cc8da39a | | RoboBrain2-7B | 37.4 | Not recorded | 697c3af0a8b01e76cc8da39a | | GPT-4V | 32.2 | Not recorded | 697c3af0a8b01e76cc8da39a | ### Thinker-7B BLEU-1: 72.7. Result ID: 69977da35698665ec4d22648. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### RoboBrain-7B BLEU-1: 72.05. Result ID: 69977da35698665ec4d22646. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### ThinkAct-7B BLEU-1: 69.1. Result ID: 69977da35698665ec4d22645. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B BLEU-1: 62.2. Result ID: 69977da35698665ec4d22643. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### RoboBrain2-7B BLEU-1: 37.4. Result ID: 69977da35698665ec4d22647. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### GPT-4V BLEU-1: 32.2. Result ID: 69977da35698665ec4d22644. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.