Benchmark
GEditBench v2 - Visual Consistency
- Models measured
- 12
- Scores recorded
- 14
- Sources
- 1
- IQ weight
- 0.14
Score distribution
- 990.8
- Mean
- 1,017
- Median
- 79
- Std dev
- 846
- 10th percentile
- 1,108
- 90th percentile
- 840
- Min
This benchmark has a weight of 0.14 for image-generation models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GLM-Image· GEditBench v2 | 1,109 |
| 2 | Gemini 3 Pro Image· GEditBench v2 | 1,108 |
| 3 | FLUX.2 [klein] 4B· GEditBench v2 | 1,070 |
| 4 | Doubao Seedream 4.5· GEditBench v2 | 1,030 |
| 5 | FLUX.2 [klein] 9B· GEditBench v2 | 1,019 |
| 6 | FLUX.2 [dev]· GEditBench v2 | 1,018 |
| 7 | Longcat Image Edit· GEditBench v2 | 1,017 |
| 8 | BAGEL· GEditBench v2 | 987 |
| 9 | Qwen Image Edit2511· GEditBench v2 | 972 |
| 10 | Qwen Image Edit· GEditBench v2 | 971 |
| 11 | Qwen Image Edit2509· GEditBench v2 | 955 |
| 12 | omnigen-v2· GEditBench v2 | 929 |
| 13 | GPT Image 1.5· GEditBench v2 | 846 |
| 14 | Flux Kontext Dev· GEditBench v2 | 840 |