Benchmark
GEditBench v2 - Overall
- Models measured
- 12
- Scores recorded
- 14
- Sources
- 1
- IQ weight
- 1.31
Score distribution
- 998.7
- Mean
- 1,014
- Median
- 75
- Std dev
- 869
- 10th percentile
- 1,089
- 90th percentile
- 851
- Min
This benchmark has a weight of 1.31 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 | Gemini 3 Pro Image· GEditBench v2 | 1,096 |
| 2 | Doubao Seedream 4.5· GEditBench v2 | 1,089 |
| 3 | GPT Image 1.5· GEditBench v2 | 1,071 |
| 4 | FLUX.2 [klein] 9B· GEditBench v2 | 1,039 |
| 5 | Qwen Image Edit2511· GEditBench v2 | 1,038 |
| 6 | FLUX.2 [klein] 4B· GEditBench v2 | 1,031 |
| 7 | Qwen Image Edit2509· GEditBench v2 | 1,014 |
| 8 | Qwen Image Edit· GEditBench v2 | 1,010 |
| 9 | FLUX.2 [dev]· GEditBench v2 | 1,006 |
| 10 | Longcat Image Edit· GEditBench v2 | 1,001 |
| 11 | GLM-Image· GEditBench v2 | 979 |
| 12 | omnigen-v2· GEditBench v2 | 888 |
| 13 | Flux Kontext Dev· GEditBench v2 | 869 |
| 14 | BAGEL· GEditBench v2 | 851 |