multimodal benchmark
TVBench Leaderboard
TVBench is a multimodal benchmark for temporal video understanding that evaluates reasoning over actions, events, and temporal dynamics in videos.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
TVBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score80.50% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score78.20% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelBY | Score77.20% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
TVBench Highlights
The leading models and scores on this benchmark.
TVBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for TVBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is TVBench?
What TVBench measures and how its scores work.
TVBench is a temporal video understanding benchmark.
It measures reasoning over actions, events, and temporal dynamics in videos.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TVBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about TVBench.
Which model scores highest on TVBench?
Seed 2.1 Pro is currently ranked first with 80.50%.
What are the top three models on TVBench?
The current leaders are Seed 2.1 Pro (80.50%), Qwen3.7-Plus (78.20%), and Seed 2.1 Turbo (77.20%).
Which TVBench model has the lowest official input price?
Qwen3.7-Plus has the lowest matched official input price at $0.50 input / $3.0 output per 1M tokens.
Which models are fastest among TVBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.