DistortBench - Spatial: 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 eight spatial distortions (jitter, non-eccentricity, pixelate, quantization, color block, sharpen, two rotations), in percent; higher is better.
Metric: Joint accuracy (%) on the eight spatial distortions (jitter, non-eccentricity, pixelate, quantization, color block, sharpen, two rotations), 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 27B | Non-reasoning | 64.8 | #380 |
| 2 | Qwen 3.5 35B A3B | 60.1 | #494 | |
| 3 | Qwen 3.5 4B | Non-reasoning | 58.1 | #1270 |
| 4 | Qwen 3.5 9B | 57.8 | #838 | |
| 5 | Kimi-VL-A3B-Instruct | 53 | #2272 | |
| 6 | InternVL3.5-38B | 52.5 | #1026 | |
| 7 | GPT-5.4 | 49.8 | #138 | |
| 8 | Gemma 3 27B | 46.8 | #1672 | |
| 9 | Gemma 3 12B | 46.3 | #2091 | |
| 10 | Kimi-VL-A3B (Thinking) | 44.5 | ||
| 11 | InternVL3.5-8B | 41.5 | #1618 | |
| 12 | InternVL3.5-14B | 37 | #1519 | |
| 13 | Qwen 2 VL 7B | 35.9 | #2300 | |
| 14 | Gemma 3 4B | 33.4 | #5347 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=distortbench-spatial · How It Works · Data refreshed daily, snapshot 2026-11-22.