Segment Anything with Concepts
Models find every instance of a concept named in a prompt. The benchmark compares image masks and video tracks with human annotations.
The report includes Gold, Silver, Bronze, and Bio image sets and the VEval video set.
- Made by
- Meta
- Released
- November 2025
- Kind
- Detection and captioning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Image, video and 3D generation
SAM 3 tops the leaderboard with 54.1%
Best score per entry from SOTA2’s leaderboard, read on November 20th, 2026. The headline is Gold cgF1 for image segmentation, the measure used to rank this leaderboard. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 SAM 3 54.1%
- 2 OWLv2 training=partially trained on LVIS 24.6%
- 3 DINO-X 21.3%
- 4 APE-D training=partially trained on LVIS 16.4%
- 5 Gemini 2.5 13%
- 6 LLMDet-L 6.50%
- 7 gDino-T 3.30%
Source: SOTA2’s leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | SAM 3 | 54.1% | Official leaderboard | ||
| 2 | OWLv2 | 24.6% | training=partially trained on LVIS | Official leaderboard | |
| 3 | DINO-X | 21.3% | Official leaderboard | ||
| 4 | APE-D | 16.4% | training=partially trained on LVIS | Official leaderboard | |
| 5 | Gemini 2.5 | 13% | Official leaderboard | ||
| 6 | LLMDet-L | 6.50% | Official leaderboard | ||
| 7 | gDino-T | 3.30% | Official leaderboard |
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 7 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on SOTA2: 7 entries at the last read, none a model we track.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.