Widget Captioning
Models describe an individual interface element in a mobile screenshot. The benchmark compares their captions with human descriptions of the same element.
- Made by
- Google Research
- Released
- October 2020
- Kind
- Documents, charts and text in images
- Level
- School
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
Pixel+Local+Context (PLC) tops the leaderboard with 44.9
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports several captioning metrics, so the headline is full-test BLEU-1, the first metric in Table 3. 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 Pixel+Local+Context (PLC) Full Test Set 44.9
- 2 Pixel+Local Full Test Set 42.6
- 3 PLC Classification Full Test Set 36.2
- 4 Pixel Only Full Test Set 35.6
Source: The Widget Captioning paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Pixel+Local+Context (PLC) | 44.9 | Full Test Set | Official leaderboard | |
| 2 | Pixel+Local | 42.6 | Full Test Set | Official leaderboard | |
| 3 | PLC Classification | 36.2 | Full Test Set | Official leaderboard | |
| 4 | Pixel Only | 35.6 | Full Test Set | 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 7 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Pass Independent runs Scores from the benchmark’s paper (4 entries).
- Note Models scored 4 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 4 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.