DistortBench - Blur: leaderboard
DistortBench (2026) shows a vision-language model a distorted photo without its original and asks it to name the distortion type and severity among four options (chance 25 percent). Joint accuracy on the three blur types (Gaussian, lens, motion), in percent; higher is better.
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 February 2027. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3.5 35B A3B | 68.3 | #492 | |
| 2 | Qwen 3.5 4B | Non-reasoning | 65.5 | #1241 |
| 3 | InternVL3.5-38B | 64.6 | #1021 | |
| 4 | GPT-5.4 | 63.9 | #135 | |
| 5 | Kimi-VL-A3B-Instruct | 63.7 | #2253 | |
| 6 | Qwen 3.5 27B | 63 | #375 | |
| 7 | Qwen 3.5 9B | 59.4 | #828 | |
| 8 | Gemma 3 27B | 59 | #1663 | |
| 9 | Gemma 3 12B | 58.6 | #2059 | |
| 10 | InternVL3.5-8B | 58.3 | #1604 | |
| 11 | InternVL3.5-14B | 54.3 | #1504 | |
| 12 | Kimi-VL-A3B (Thinking) | 51.8 | ||
| 13 | Gemma 3 4B | 45.8 | #5339 | |
| 14 | Qwen 2 VL 7B | 44.1 | #2275 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=distortbench-blur · How It Works · Data refreshed daily, snapshot 2026-11-21.