Benchmark
GEditBench v2 - Visual Quality
- Models measured
- 12
- Scores recorded
- 14
- Sources
- 1
- IQ weight
- 1.37
Score distribution
- 1,004
- Mean
- 1,025
- Median
- 111.7
- Std dev
- 900
- 10th percentile
- 1,142
- 90th percentile
- 694
- Min
This benchmark has a weight of 1.37 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 | GPT Image 1.5· GEditBench v2 | 1,149 |
| 2 | Doubao Seedream 4.5· GEditBench v2 | 1,142 |
| 3 | Qwen Image Edit· GEditBench v2 | 1,073 |
| 4 | Gemini 3 Pro Image· GEditBench v2 | 1,066 |
| 5 | Qwen Image Edit2509· GEditBench v2 | 1,062 |
| 6 | Qwen Image Edit2511· GEditBench v2 | 1,060 |
| 7 | FLUX.2 [klein] 9B· GEditBench v2 | 1,025 |
| 8 | GLM-Image· GEditBench v2 | 1,023 |
| 9 | FLUX.2 [klein] 4B· GEditBench v2 | 1,019 |
| 10 | Longcat Image Edit· GEditBench v2 | 968 |
| 11 | FLUX.2 [dev]· GEditBench v2 | 965 |
| 12 | omnigen-v2· GEditBench v2 | 910 |
| 13 | Flux Kontext Dev· GEditBench v2 | 900 |
| 14 | BAGEL· GEditBench v2 | 694 |