LVBench evaluates long-video understanding across extended videos such as television, sports and surveillance footage. It measures information extraction, temporal grounding, reasoning and summarization over videos whose duration can span hours.
Browse the latest scores, model modes, release dates, and parameter sizes for LVBench.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Gemini 3.7 Flash Thinking Level · Medium | 85.40 | 2026-08-13 | Unknown | Closed |
Google reported 85.4% for Gemini 3.7 Flash using 1,024 frames and no tools in its official model card on 2026-08-13.
