Benchmark Almanac

ArtEdit-Bench-Eval

JarvisEvo 0.72 tops its leaderboard Gemini 2.5 Flash Sep 2025 0.62 leads the models we track
Not in model cards

Models rate photo edits against English instructions. Spearman and Pearson correlations measure agreement with human ratings on 200 cases.

Tencent Hunyuan compares six evaluators, including two Qwen3-VL models and Gemini 2.5 Flash. The release includes the original photos, edited photos, and evaluation annotations.

Released
November 2025
Kind
Image generation and editing
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Subject
Arts
Language
English
In and out
Images, Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
Gemini 2.5 Flash Sep 2025 #112 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
6
Entries in its paper, 1 model we track

JarvisEvo tops the leaderboard with 0.72 Gemini 2.5 Flash leads with 0.62

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 Gemini 2.5 Flash, at 0.62. This view shows only models we track, each at its best.

  1. 1 JarvisEvo Instruction following and image quality 0.72
  2. 2 Gemini 2.5 Flash Sep 2025, Instruction following and image quality 0.62
  3. 3 Qwen3-VL-256B-A22B Instruction following and image quality 0.57
  4. 4 VisualQuality-R1 Fixed prompt, image quality only 0.56
  5. 5 Q-insight Fixed prompt, image quality only 0.54
  6. 6 Qwen3-VL-8B Instruction following and image quality 0.47

Source: The ArtEdit-Bench-Eval paper

Source: The ArtEdit-Bench-Eval paper

#EntryScoreSettingDateSource
1 JarvisEvo 0.72 Instruction following and image quality Official leaderboard
2 Gemini 2.5 Flash Sep 2025 0.62 Instruction following and image quality Sep 2025 Official leaderboard
3 Qwen3-VL-256B-A22B 0.57 Instruction following and image quality Official leaderboard
4 VisualQuality-R1 0.56 Fixed prompt, image quality only Official leaderboard
5 Q-insight 0.54 Fixed prompt, image quality only Official leaderboard
6 Qwen3-VL-8B 0.47 Instruction following and image quality Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 2.5 Flash Sep 2025 0.62 Instruction following and image quality 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
0.62 0.62

Source: Official ArtEdit-Bench-Eval 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 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (6 entries).
  • Pass Models scored 1 model we track, plus 5 other entries on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Flash (#112).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 1 row for models we track and 5 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