Tricky Edits of Collected and Curated Images
Models edit a source image to follow a written instruction. People and a model judge instruction following, preservation of unaffected content, and visual quality.
The authors publish results for five image editors on the benchmark site. Human graders score a subset and an automated grader scores the full set.
- Made by
- Google DeepMind
- Released
- May 2026
- Kind
- Image generation and editing
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- 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
- Last model added
- February 2026
- Scores refreshed
- November 21st, 2026
Nano Banana Pro tops the leaderboard with 19.8% Gemini 3.1 Flash Image leads with 19.5% among models released by February 2026
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is Gemini 3.1 Flash Image, at 19.5%. This view shows only models we track, each at its best.
The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 Nano Banana Pro autorater, full benchmark 19.8%
- 2
Gemini 3.1 Flash Image autorater, full benchmark 19.5%
- 3 Grok Imagine Pro autorater, full benchmark 19.3%
- 4
Seedream 5.0 Lite autorater, full benchmark 18.6%
- 5 GPT-Image-1.5 autorater, full benchmark 4.70%
Source: The Tricky Edits of Collected and Curated Images paper
Source: The Tricky Edits of Collected and Curated Images paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Nano Banana Pro | 19.8% | autorater, full benchmark | Official leaderboard | |
| 2 | | 19.5% | autorater, full benchmark | Feb 2026 | Official leaderboard |
| 3 | Grok Imagine Pro | 19.3% | autorater, full benchmark | Official leaderboard | |
| 4 | | 18.6% | autorater, full benchmark | Official leaderboard | |
| 5 | GPT-Image-1.5 | 4.70% | autorater, full benchmark | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 19.5% | autorater, full benchmark | Feb 2026 | Official leaderboard |
| 2 | | 18.6% | autorater, full benchmark | Official leaderboard | |
| 3 | GPT-Image-1.5 | 4.70% | autorater, full benchmark | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Tricky Edits of Collected and Curated Images 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 9 months ago, in February 2026, for Gemini 3.1 Flash Image. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (5 entries).
- Pass Models scored 3 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 9 months ago, in February 2026, for Gemini 3.1 Flash Image.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 19.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on google-deepmind.github.io: 3 rows for models we track and 2 other entries at the last read.
- Pass Last read November 21st, 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.