AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
LVBench
LVBench is an extreme long video understanding benchmark designed to evaluate multimodal models on videos up to two hours in duration. It contains 6 major categories and 21 subcategories, with videos averaging five times longer than existing datasets. The benchmark addresses applications requiring comprehension of extremely long videos.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- multimodal
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 25
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Gemini 3.7 Flash | 0.854 | Not recorded | Not recorded | 2026-08-13 · model_announcement | LLM Stats |
| Qwen3.8 Max | 0.818 | Not recorded | Not recorded | 2026-08-02 · model_announcement | LLM Stats |
| Seed 2.1 Pro | 0.78 | Not recorded | Not recorded | 2026-06-24 · model_announcement | LLM Stats |
| Seed 2.1 Turbo | 0.768 | Not recorded | Not recorded | 2026-06-24 · model_announcement | LLM Stats |
| Qwen3.7-Plus | 0.762 | Not recorded | Not recorded | 2026-05-31 · model_announcement | LLM Stats |
| Kimi K2.5 | 0.759 | Not recorded | Not recorded | 2026-01-27 · model_announcement | LLM Stats |
| Qwen3.5-122B-A10B | 0.744 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3.5-27B | 0.736 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3.6-35B-A3B | 0.714 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| Qwen3.5-35B-A3B | 0.714 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Instruct | 0.677 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 32B Instruct | 0.638 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Thinking | 0.636 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 32B Thinking | 0.626 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Instruct | 0.625 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Thinking | 0.592 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 8B Instruct | 0.58 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 4B Instruct | 0.562 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 8B Thinking | 0.558 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 4B Thinking | 0.535 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen2.5 VL 32B Instruct | 0.49 | Not recorded | Not recorded | 2025-02-28 · model_announcement | LLM Stats |
| Qwen2.5 VL 72B Instruct | 0.473 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Qwen2.5 VL 7B Instruct | 0.453 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Nova Pro | 0.416 | Not recorded | Not recorded | 2024-11-20 · model_announcement | LLM Stats |
| Nova Lite | 0.404 | Not recorded | Not recorded | 2024-11-20 · model_announcement | LLM Stats |