long context benchmark
LongVideoBench Leaderboard
LongVideoBench is a question-answering benchmark featuring video-language interleaved inputs up to an hour long. It includes 3,763 varying-length web-collected videos with subtitles across diverse themes and 6,678 human-annotated multiple-choice questions in 17 fine-grained categories for comprehensive evaluation of long-term multimodal understanding.
Updated Aug 17, 2026
Models4
Model coverage4
MetricScore
EvidenceB
LongVideoBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score80.6% | Percentile100.0% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score80.6% | Percentile66.7% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score79.8% | Percentile33.3% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score54.7% | Percentile0.0% | Participants4 | EvidenceC | Evaluated |
LongVideoBench Highlights
The leading models and scores on this benchmark.
LongVideoBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LongVideoBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis longvideobench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01BYSeed 2.1 ProByteDance
- Score
- 80.6%
Strengths
- Ranks #1 of 4 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures LongVideoBench, not total model capability
- 02BYSeed 2.1 TurboByteDance
- Score
- 80.6%
Strengths
- Ranks #2 of 4 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures LongVideoBench, not total model capability
- 03MAKimi K2.5Moonshot AI
- Score
- 79.8%
- Price
- $0.60 input / $3.0 output per 1M tokens
Strengths
- Ranks #3 of 4 compared models
- 33th percentile on this benchmark
- C evidence result
Considerations
- This result measures LongVideoBench, not total model capability
- 04ACQwen2.5 VL 7B InstructAlibaba Cloud / Qwen Team
- Score
- 54.7%
- Price
- $0.35 input / $1.1 output per 1M tokens
Strengths
- Ranks #4 of 4 compared models
- 0th percentile on this benchmark
- C evidence result
Considerations
- This result measures LongVideoBench, not total model capability
Selection summary
Best AI Models for LongVideoBench
Seed 2.1 Pro currently leads LongVideoBench with 80.6%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is LongVideoBench?
What LongVideoBench measures and how its scores work.
LongVideoBench is a question-answering benchmark featuring video-language interleaved inputs up to an hour long. It includes 3,763 varying-length web-collected videos with subtitles across diverse themes and 6,678 human-annotated multiple-choice questions in 17 fine-grained categories for comprehensive evaluation of long-term multimodal understanding.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- LongVideoBench
- Modality
- multimodal
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- longvideobench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about LongVideoBench.
Which model scores highest on LongVideoBench?
Seed 2.1 Pro is currently ranked first with 80.6%.
What does LongVideoBench measure?
LongVideoBench is a question-answering benchmark featuring video-language interleaved inputs up to an hour long. It includes 3,763 varying-length web-collected videos with subtitles across diverse themes and 6,678 human-annotated multiple-choice questions in 17 fine-grained categories for comprehensive evaluation of long-term multimodal understanding.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.