# VideoQA > DeepMind's 1H-VideoQA tests recall and reasoning over videos lasting 40 to 90 minutes. The current 101-question, five-choice task remains separate from the original 126-question set. Canonical page: https://benchlm.ai/benchmarks/video-qa - Category: [Multimodal & Grounded](/multimodal-grounded) - Last updated: October 9, 2026 Evaluation results published by [Google DeepMind, Google Research, and Kaggle](https://www.kaggle.com/benchmarks/deepmind/video-qa). undefined Kaggle labels this benchmark Apache 2.0. We retain aggregate measurements with attribution and source links. That declaration does not establish rights to third-party documents, videos, or other underlying task material; no task contents are included. [Original article terms](https://www.apache.org/licenses/LICENSE-2.0). VideoQA uses 101 five-choice questions about videos lasting 40 to 90 minutes. The source recommends one frame per second, uniform subsampling when context is limited, and zero-shot prompting; audio is optional. Accuracy counts the selected correct answers. The current set is smaller than the original 126-question release because questions are removed when their YouTube videos disappear. The download does not disclose every model's frame count, audio use, or generation settings, so this table does not establish identical input budgets. Kaggle labels the benchmark Apache 2.0, while the separate dataset card lists its license as Unknown; no videos, prompts, or answers are reproduced. The complete official download includes models hidden by the source page's default filters. Source names and task versions stay separate from canonical model profiles; these results do not enter overall or category rankings. These are published source configurations. Compare the task version and disclosed settings before treating a score difference as a model difference. - [Official Kaggle leaderboard](https://www.kaggle.com/benchmarks/deepmind/video-qa) - [Official leaderboard JSON](https://www.kaggle.com/api/v1/benchmarks/deepmind/video-qa/leaderboard) - [Evaluation method](https://arxiv.org/abs/2403.05530) - [Benchmark-page Apache 2.0 declaration](https://www.apache.org/licenses/LICENSE-2.0) ## About VideoQA - Year: 2024 - Tasks: 101 five-choice questions about videos lasting 40 to 90 minutes - Format: Zero-shot long-video multiple-choice answering - Paper: [VideoQA methodology](https://arxiv.org/abs/2403.05530) VideoQA uses 101 five-choice questions about videos lasting 40 to 90 minutes. The source recommends one frame per second, uniform subsampling when context is limited, and zero-shot prompting; audio is optional. Accuracy counts the selected correct answers. The current set is smaller than the original 126-question release because questions are removed when their YouTube videos disappear. The download does not disclose every model's frame count, audio use, or generation settings, so this table does not establish identical input budgets. Kaggle labels the benchmark Apache 2.0, while the separate dataset card lists its license as Unknown; no videos, prompts, or answers are reproduced. The complete official download includes models hidden by the source page's default filters. Source names and task versions stay separate from canonical model profiles; these results do not enter overall or category rankings. VideoQA is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula. ## Leaderboard (20 source rows) | Rank | Model | Configuration | Creator | Score | |------|-------|---------------|---------|-------| | 1 | [Gemini 3.7 Flash](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-08-27 | — | 89.1% | | 2 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-09-10 | — | 87.1% | | 3 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-10-09 | — | 87.0% | | 4 | [Gemini 3.6 Flash](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-07-30 | — | 82.2% | | 5 | [Gemini 3.5 Flash](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-06-08 | — | 80.2% | | 6 | [Gemini 3 Flash Preview](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-05-18 | — | 79.2% | | 7 | [Gemini 2.5 Pro](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-06-08 | — | 78.9% | | 8 | [Gemini 3.1 Pro Preview](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-06-08 | — | 78.2% | | 9 | [Gemini 3.1 Flash-Lite Preview](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-06-08 | — | 78.2% | | 10 | [Gemini 3.5 Flash-Lite](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-07-30 | — | 75.2% | | 11 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-09-17 | — | 75.2% | | 12 | [Claude Opus 4.8](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-06-08 | — | 71.3% | | 13 | [Claude Haiku 5.5](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-10-09 | — | 68.3% | | 14 | [Claude Sonnet 4.6](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-05-18 | — | 67.3% | | 15 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-07-30 | — | 67.3% | | 16 | [GPT-6 Sol](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-09-26 | — | 66.3% | | 17 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-07-30 | — | 62.4% | | 18 | [Grok 4.6](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-09-17 | — | 60.0% | | 19 | [Grok 4.7](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-10-22 | — | 59.4% | | 20 | [GPT-6 Luna](https://www.kaggle.com/benchmarks/deepmind/video-qa) | Kaggle benchmark v1; task revision 21; Evaluated 2026-09-26 | — | 57.4% | ## FAQ ### What does VideoQA measure? DeepMind's 1H-VideoQA tests recall and reasoning over videos lasting 40 to 90 minutes. The current 101-question, five-choice task remains separate from the original 126-question set. ### Which source row has the highest reported VideoQA value? Gemini 3.7 Flash has the highest reported VideoQA value at 89.1%. These are published source configurations. Compare the task version and disclosed settings before treating a score difference as a model difference. ### How many models are evaluated on VideoQA? The October 9, 2026 contains 20 AI models. ### Does VideoQA affect BenchLM's overall score? Not directly. VideoQA is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.