multimodal benchmark
CharadesSTA Leaderboard
Charades-STA is a benchmark dataset for temporal activity localization via language queries, extending the Charades dataset with sentence temporal annotations. It contains 12,408 training and 3,720 testing segment-sentence pairs from videos with natural language descriptions and precise temporal boundaries for localizing activities based on language queries.
Updated Aug 17, 2026
Models12
Model coverage12
MetricScore
EvidenceB
CharadesSTA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score64.8% | Percentile100.0% | Participants12 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score63.5% | Percentile90.9% | Participants12 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score63.5% | Percentile81.8% | Participants12 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score62.8% | Percentile72.7% | Participants12 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score62.7% | Percentile63.6% | Participants12 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score61.2% | Percentile54.5% | Participants12 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score59.9% | Percentile45.5% | Participants12 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score59.0% | Percentile36.4% | Participants12 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score56.0% | Percentile27.3% | Participants12 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score55.5% | Percentile18.2% | Participants12 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score54.2% | Percentile9.1% | Participants12 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score43.6% | Percentile0.0% | Participants12 | EvidenceC | Evaluated |
CharadesSTA Highlights
The leading models and scores on this benchmark.
CharadesSTA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CharadesSTA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis charadessta 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.
- 01ACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen Team
- Score
- 64.8%
Strengths
- Ranks #1 of 12 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharadesSTA, not total model capability
- 02ACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen Team
- Score
- 63.5%
Strengths
- Ranks #2 of 12 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharadesSTA, not total model capability
- 03ACQwen3 VL 30B A3B InstructAlibaba Cloud / Qwen Team
- Score
- 63.5%
Strengths
- Ranks #3 of 12 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharadesSTA, not total model capability
- 04ACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen Team
- Score
- 62.8%
Strengths
- Ranks #4 of 12 compared models
- 73th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharadesSTA, not total model capability
- 05ACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen Team
- Score
- 62.7%
Strengths
- Ranks #5 of 12 compared models
- 64th percentile on this benchmark
- C evidence result
Considerations
- This result measures CharadesSTA, not total model capability
Selection summary
Best AI Models for CharadesSTA
Qwen3 VL 235B A22B Instruct currently leads CharadesSTA with 64.8%. 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 CharadesSTA?
What CharadesSTA measures and how its scores work.
Charades-STA is a benchmark dataset for temporal activity localization via language queries, extending the Charades dataset with sentence temporal annotations. It contains 12,408 training and 3,720 testing segment-sentence pairs from videos with natural language descriptions and precise temporal boundaries for localizing activities based on language queries.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CharadesSTA
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- charadessta|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CharadesSTA.
Which model scores highest on CharadesSTA?
Qwen3 VL 235B A22B Instruct is currently ranked first with 64.8%.
What does CharadesSTA measure?
Charades-STA is a benchmark dataset for temporal activity localization via language queries, extending the Charades dataset with sentence temporal annotations. It contains 12,408 training and 3,720 testing segment-sentence pairs from videos with natural language descriptions and precise temporal boundaries for localizing activities based on language queries.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
12 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.