GEBench
Image generation models create interactive GUI states from prompts. A judge scores goal, logic, consistency, interface and quality across five task types.
The release contains 700 samples in five categories and reports Chinese and English results for 12 models.
- Made by
- StepFun and collaborators
- Released
- February 2026
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- Many languages
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Image, video and 3D generation, Many languages
- Scores refreshed
- November 21st, 2026
Nano Banana Pro tops the leaderboard with 69.6 GPT-Image-1.5 leads with 63.2
Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. 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 GPT-Image-1.5, at 63.2. This view shows only models we track, each at its best.
- 1 Nano Banana Pro Chinese 69.6
- 2 GPT-Image-1.5 Chinese 63.2
- 3 FLUX.2 [pro] Chinese 57.5
- 4 Nano Banana Chinese 56.7
- 5
Seedream 4.5 Chinese 55.9
- 6 GPT-Image-1 English 55.6
- 7
Wan 2.6 Chinese 55.4
- 8
Seedream 4.0 Chinese 52.9
- 9 UniWorld-V2 Chinese 36.7
- 10 Longcat-Image Chinese 34.5
- 11
Qwen-Image-Edit Chinese 33.7
- 12
BAGEL Chinese 28.9
Source: Official GEBench leaderboard
- 1 GPT-Image-1.5 Chinese 63.2
- 2 FLUX.2 [pro] Chinese 57.5
- 3
Seedream 4.5 Chinese 55.9
- 4 GPT-Image-1 English 55.6
- 5
Wan 2.6 Chinese 55.4
- 6
Seedream 4.0 Chinese 52.9
- 7
Qwen-Image-Edit Chinese 33.7
- 8
BAGEL Chinese 28.9
Source: Official GEBench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Nano Banana Pro | 69.6 | Chinese | Official leaderboard | |
| 2 | GPT-Image-1.5 | 63.2 | Chinese | Official leaderboard | |
| 3 | FLUX.2 [pro] | 57.5 | Chinese | Official leaderboard | |
| 4 | Nano Banana | 56.7 | Chinese | Official leaderboard | |
| 5 | | 55.9 | Chinese | Official leaderboard | |
| 6 | GPT-Image-1 | 55.6 | English | Official leaderboard | |
| 7 | | 55.4 | Chinese | Official leaderboard | |
| 8 | | 52.9 | Chinese | Official leaderboard | |
| 9 | UniWorld-V2 | 36.7 | Chinese | Official leaderboard | |
| 10 | Longcat-Image | 34.5 | Chinese | Official leaderboard | |
| 11 | | 33.7 | Chinese | Official leaderboard | |
| 12 | | 28.9 | Chinese | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-Image-1.5 | 63.2 | Chinese | Official leaderboard | |
| 2 | FLUX.2 [pro] | 57.5 | Chinese | Official leaderboard | |
| 3 | | 55.9 | Chinese | Official leaderboard | |
| 4 | GPT-Image-1 | 55.6 | English | Official leaderboard | |
| 5 | | 55.4 | Chinese | Official leaderboard | |
| 6 | | 52.9 | Chinese | Official leaderboard | |
| 7 | | 33.7 | Chinese | Official leaderboard | |
| 8 | | 28.9 | Chinese | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Single-Step, Multi-Step and Fiction-App. GPT-Image-1.5 leads 2 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Single-Step
8 models we track have a score here.
- 1 GPT-Image-1.5 83.8
- 2 FLUX.2 [pro] 68.8
- 3 GPT-Image-1 ↑1 64.7
- 4
Wan 2.6 ↑1 64.2
- 5
Seedream 4.5 ↓2 63.6
- 6
Seedream 4.0 62.0
- 7
Qwen-Image-Edit 41.1
- 8
BAGEL 34.8
Multi-Step
8 models we track have a score here.
- 1 GPT-Image-1 ↑3 64.3
- 2 GPT-Image-1.5 ↓1 58.9
- 3 FLUX.2 [pro] ↓1 55.1
- 4
Seedream 4.5 ↓1 53.1
- 5
Wan 2.6 50.1
- 6
Seedream 4.0 48.6
- 7
Qwen-Image-Edit 26.8
- 8
BAGEL 13.4
Fiction-App
8 models we track have a score here.
- 1 GPT-Image-1.5 63.7
- 2 GPT-Image-1 ↑2 58.9
- 3 FLUX.2 [pro] ↓1 58.1
- 4
Seedream 4.5 ↓1 56.5
- 5
Wan 2.6 52.7
- 6
Seedream 4.0 49.3
- 7
BAGEL ↑1 27.4
- 8
Qwen-Image-Edit ↓1 25.8
Real-App
8 models we track have a score here.
- 1 GPT-Image-1 ↑3 59.0
- 2 GPT-Image-1.5 ↓1 58.9
- 3 FLUX.2 [pro] ↓1 55.4
- 4
Seedream 4.5 ↓1 53.4
- 5
Seedream 4.0 ↑1 50.9
- 6
Wan 2.6 ↓1 50.4
- 7
BAGEL ↑1 35.1
- 8
Qwen-Image-Edit ↓1 26.1
Grounding
8 models we track have a score here.
- 1
Wan 2.6 ↑4 59.6
- 2
Qwen-Image-Edit ↑5 54.5
- 3
Seedream 4.0 ↑3 53.5
- 4 GPT-Image-1.5 ↓3 53.3
- 5
Seedream 4.5 ↓2 52.9
- 6 FLUX.2 [pro] ↓4 50.2
- 7 GPT-Image-1 ↓3 37.8
- 8
BAGEL 37.3
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official GEBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-Image-1.5 | Chinese | 63.2 | |||
| GPT-Image-1.5 | English | 63.2 | |||
| FLUX.2 [pro] | Chinese | 57.5 | |||
| Chinese | 55.9 | ||||
| GPT-Image-1 | English | 55.6 | |||
| Chinese | 55.4 | ||||
| Chinese | 52.9 | ||||
| GPT-Image-1 | Chinese | 52.4 | |||
| FLUX.2 [pro] | English | 51.2 | |||
| English | 50.5 | ||||
| English | 50.0 | ||||
| English | 46.5 | ||||
| Chinese | 33.7 | ||||
| English | 33.0 | ||||
| Chinese | 28.9 | ||||
| English | 28.0 |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official GEBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-Image-1.5 | Chinese | 63.2 | |||
| GPT-Image-1.5 | English | 63.2 | |||
| FLUX.2 [pro] | Chinese | 57.5 | |||
| Chinese | 55.9 | ||||
| GPT-Image-1 | English | 55.6 | |||
| Chinese | 55.4 | ||||
| Chinese | 52.9 | ||||
| GPT-Image-1 | Chinese | 52.4 | |||
| FLUX.2 [pro] | English | 51.2 | |||
| English | 50.5 | ||||
| English | 50.0 | ||||
| English | 46.5 | ||||
| Chinese | 33.7 | ||||
| English | 33.0 | ||||
| Chinese | 28.9 | ||||
| English | 28.0 |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No dated values yet.
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 (12 entries).
- Pass Models scored 8 models we track, plus 4 other entries on its leaderboard.
- Note Newest score No scores yet.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on stepfun-ai.github.io: 16 rows for models we track and 4 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.