Benchmark Almanac

Aether-Bench

Flux.1 Kontext 89.8% tops its leaderboard Qwen-Image-Edit-2509 79.7% leads the models we track
Not in model cards

Models retouch photographs automatically, match a requested style, or apply specified adjustments. The style test measures fidelity on 100 image pairs from unseen presets, including peak signal-to-noise ratio.

Beijing Academy of Artificial Intelligence’s community site covered the style results. The authors compare Nano Banana, Qwen-Image-2509, and other editors across three tasks.

Released
April 2026
Kind
Image generation and editing
Level
University
Scored
Checked automatically
Answers
Open-ended
Measures
Capability
Subject
Arts
Language
English
In and out
Text, Images → Images
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
Anyone
Last model added
September 2025
Scores refreshed
November 20th, 2026
8
Entries in its paper, 1 model we track

Flux.1 Kontext tops the leaderboard with 89.8% Qwen-Image-Edit-2509 leads with 79.7%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports separate metrics for three tasks. The headline is Auto Hist-M, the first metric. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen-Image-Edit-2509, at 79.7%. This view shows only models we track, each at its best.

  1. 1 Flux.1 Kontext 89.8%
  2. 2 VeraRetouch-DAPO-AE 89.6%
  3. 3 RSFNet 89.2%
  4. 4 VeraRetouch-SFT 88.5%
  5. 5 Nano Banana 86.4%
  6. 6 MonetGPT 85%
  7. 7 JarvisArt 81.1%
  8. 8 Qwen-Image-Edit-2509 79.7%

Source: The Aether-Bench paper

Source: The Aether-Bench paper

#EntryScoreSettingDateSource
1 Flux.1 Kontext 89.8% Official leaderboard
2 VeraRetouch-DAPO-AE 89.6% Official leaderboard
3 RSFNet 89.2% Official leaderboard
4 VeraRetouch-SFT 88.5% Official leaderboard
5 Nano Banana 86.4% Official leaderboard
6 MonetGPT 85% Official leaderboard
7 JarvisArt 81.1% Official leaderboard
8 Qwen-Image-Edit-2509 79.7% Sep 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen-Image-Edit-2509 79.7% Sep 2025 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Qwen-Image-Edit-2509 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Qwen-Image-Edit-2509

Source: Official Aether-Bench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

8 of 10 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (8 entries).
  • Pass Models scored 1 model we track, plus 7 other entries on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Qwen-Image-Edit-2509.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 79.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 1 row for models we track and 7 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check