Charades-STA
Seed1.5-VL 64% leads since May 2025 Dropped Models read a sentence describing an action and return its start and end time in a Charades indoor video. Scored by temporal IoU with the labeled moment.
Built on the Charades videos with added sentence and time labels. Labs report mIoU or recall at IoU 0.5.
In the authors’ words
This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist of a wide combination of actors, actions and objects; it is difficult to design a proper activity list that meets users' needs. We propose to localize activities by natural language queries. Temporal Activity Localization via Language (TALL) is challenging as it requires: (1) suitable design of text and video representations to allow cross-modal matching of actions and language queries; (2) ability to locate actions accurately given features from sliding windows of limited granularity. We propose a novel Cross-modal Temporal Regression Localizer (CTRL) to jointly model text query and video clips, output alignment scores and action boundary regression results for candidate clips. For evaluation, we adopt TaCoS dataset, and build a new dataset for this task on top of Charades by adding sentence temporal annotations, called Charades-STA. We also build complex sentence queries in Charades-STA for test. Experimental results show that CTRL outperforms previous methods significantly on both datasets.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
Seed1.5-VL leads with 64% among models released by Sep 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Sep 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Seed1.5-VL 64%
- 2
Qwen3-VL-235B-A22B 63.5% - 3 Qwen2.5-VL-72B 50.9%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Seed1.5-VL | 64% | May 2025 | Model card | |
| 2 | Qwen3-VL-235B-A22B | 63.5% | Nov 2025 | Model card | |
| 3 | Qwen2.5-VL-72B | 50.9% | Feb 2025 | Model card |
2 models have held number one since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Sep 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 23 Sep 2025 | Qwen3-VL-235B-A22B | 63.5 | CharadesSTA |
| 12 May 2025 | Seed1.5-VL | 64 | Charades-STA (mIoU) |
3 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 26 Nov 2025 | Qwen3-VL-235B-A22B technical report | 63.5 | Charades-STA mIoU (Table 2) | Capabilities |
| 11 May 2025 | Seed1.5-VL technical report | 64 | Charades-STA, mIoU, thinking (Table 7). Non-thinking 64.7 | Capabilities |
| 19 Feb 2025 | Qwen2.5-VL-72B technical report | 50.9 | Charades-STA mIoU (Table 8) | Capabilities |
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7% - MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%
- TVBench In use Models answer multiple-choice questions on 10 temporal video tasks, such as action counting and ordering, that static frames cannot solve. Scored by accuracy. Qwen 3.8 Max 81.9%