EditReward-Compass: leaderboard
Accuracy (%) of multimodal LLMs used as image-editing reward models at picking the preferred edit of each pair. EditReward-Compass (2026) holds 2,251 human-verified preference pairs of edited images produced by the same editing models under one instruction, as a reward model meets them during RL; higher is better.
Metric: Average preference accuracy (%) over all pairs on EditReward-Compass (2,251 human-verified preference pairs of edited images sampled from the same editing models under the same instruction), general MLLMs prompted with the Edit-Compass rubric; thinking disabled unless the row is a thinking run; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74.33 | #99 |
| 2 | Gemini 3 Flash | 72.68 | #175 |
| 3 | Qwen 3.6 27B | 71.83 | #351 |
| 4 | Qwen 3.5 35B A3B | 70.89 | #492 |
| 5 | Qwen 3.6 35B A3B | 70.51 | #481 |
| 6 | Qwen 3.5 27B | 69.98 | #375 |
| 7 | Gemma 4 31B | 67.09 | #382 |
| 8 | Qwen 3.5 9B | 66.81 | #828 |
| 9 | GPT-4.1 | 66.11 | #505 |
| 10 | Gemma 4 26B A4B | 59.6 | #590 |
| 11 | Qwen 3 VL 32B | 57.9 | #622 |
| 12 | Gemma 3 27B | 49.96 | #1663 |
| 13 | Qwen 3 VL 30B A3B | 47.87 | #784 |
| 14 | Qwen 3 VL 8B | 46.5 | #917 |
| 15 | Qwen 3 VL 4B | 43.22 | #1151 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=editreward-compass · How It Works · Data refreshed daily, snapshot 2026-11-21.