Benchmark
WISE Verified - Overall
Scores are percentages.
- Models measured
- 11
- Scores recorded
- 13
- Sources
- 1
- IQ weight
- 1.22
Score distribution
- 50.9%
- Mean
- 44%
- Median
- 15%
- Std dev
- 36.4%
- 10th percentile
- 79.5%
- 90th percentile
- 35.2%
- Min
This benchmark has a weight of 1.22 for image-generation models, measured over 10 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· WISE data | 82.5% |
| 2 | Qwen Image 2 2· WISE data | 79.5% |
| 3 | BAGELw/ CoT· WISE data | 62.8% |
| 4 | FLUX.2 [dev]· WISE data | 56.5% |
| 5 | Qwen Image· WISE data | 51% |
| 6 | Qwen Image2512· WISE data | 49.9% |
| 7 | FLUX.2 [klein] 9B· WISE data | 44% |
| 8 | Hunyuan Image V3· WISE data | 43.5% |
| 9 | FLUX.1 [dev]· WISE data | 41.6% |
| 10 | FLUX.2 [klein] 4B· WISE data | 40.1% |
| 11 | Stable Diffusion v3 Medium· WISE data | 38.5% |
| 12 | FLUX 1 Schnell· WISE data | 36.4% |
| 13 | BAGEL· WISE data | 35.2% |