DiffCap-Bench - Composition: leaderboard
DiffCap-Bench (2026) image difference captioning restricted to composition differences, including cropping. Macro-averaged F1* in percent, combining the share of true differences described and the share of described differences that are correct, as judged by Gemini 2.5 Pro; higher is better.
Metric: Macro-averaged F1* (%) on composition differences, including cropping: harmonic mean of recall* (share of key differences described) and precision* (share of described differences that are correct) on the 1,075 image pairs of DiffCap-Bench (6,713 human-verified difference items), one fixed captioning prompt, open models at temperature 0.1 and proprietary models at their defaults, a Gemini 2.5 Pro judge matching each described difference against the key difference list; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.2 | 91.5 | #190 | |
| 2 | Gemini 3 Pro | 88 | #146 | |
| 3 | Qwen 3 VL Plus | 79.3 | #514 | |
| 4 | Kimi K2.5 | Non-reasoning | 77.5 | #272 |
| 5 | Step3 VL 10B | 77.2 | #1058 | |
| 6 | Grok 4.20 | 75.8 | #307 | |
| 7 | MiMo-VL-7B-RL-2508 | 75.2 | #829 | |
| 8 | Seed1.6-VL | Thinking | 73.6 | #389 |
| 9 | Qwen 3 VL 32B Instruct | 72.3 | #607 | |
| 10 | Qwen 3 VL 8B Instruct | 69.2 | #1043 | |
| 11 | Qwen 3 VL 32B (Thinking) | 69.2 | #577 | |
| 12 | Qwen 3 VL 8B (Thinking) | 66.7 | #924 | |
| 13 | InternVL3.5-8B | 62.9 | #1618 | |
| 14 | InternVL3.5-38B | 59.2 | #1026 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=diffcap-bench-composition · How It Works · Data refreshed daily, snapshot 2026-11-22.