DistortBench - Blur: leaderboard
Metric: Joint accuracy (%) on the three blur types (Gaussian, lens, motion), a category of DistortBench's 13,500 four-choice questions (27 distortion types at five KADID-10k calibrated severity levels on 100 KADIS-700k photos, no reference image), the answer naming both type and severity, answered-only accuracy (unparseable responses, at most 3.4 percent, leave the denominator), chance 25; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 35B A3B | 68.3 |
| 2 | Qwen 3.5 35B A3B (Non-reasoning) | 66.6 |
| 3 | Qwen 3.5 4B (Non-reasoning) | 65.5 |
| 4 | GPT-5.4 | 63.9 |
| 5 | Qwen 3.5 27B | 63 |
| 6 | Qwen 3.5 4B | 62.6 |
| 7 | Qwen 3.5 27B (Non-reasoning) | 62.3 |
| 8 | Qwen 3.5 9B | 59.4 |
| 9 | Qwen 3.5 9B (Non-reasoning) | 59.1 |
| 10 | Gemma 3 27B | 59 |
| 11 | Gemma 3 12B | 58.6 |
| 12 | Gemma 3 4B | 45.8 |
| 13 | Qwen 2 VL 7B | 44.1 |
Interactive version: theaggregate.ai/benchmark?slug=distortbench-blur · How It Works · Data refreshed daily, snapshot 2026-10-07.