Benchmark Almanac

MDMR-Bench

Not in model cards

Models generate one image from several references. A model judge checks whether the output preserves requested elements, follows instructions, and combines them correctly.

Made by
Bowen Zheng and colleagues
Released
May 2026
Kind
Image generation and editing
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Images
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Last model added
February 2026
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 7 models we track

GPT-Image-2 leads with 88.8% among models released by February 2026 GPT-Image-2 leads with 88.8% among models released by February 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. This view shows only models we track, each at its best.

The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-Image-2 88.8%
  2. 2 Nano Banana Pro 85.1%
  3. 3 Gemini 3.1 Flash Image 81.2%
  4. 4 Seedream 5.0 78.8%
  5. 5 Seedream 4.0 77.8%
  6. 6 GPT-Image-1.5 77.5%
  7. 7 FLUX.2 [dev] 51.3%
  8. 8 Qwen-Image-Edit (2511) 49.9%
  9. 9 BAGEL 41.9%
  10. 10 DreamOmni2 41.9%
  11. 11 OmniGen2 28.6%

Source: Official MDMR-Bench leaderboard

#EntryScoreSettingDateSource
1 GPT-Image-2 88.8% Official leaderboard
2 Nano Banana Pro closed weights 85.1% Official leaderboard
3 Gemini 3.1 Flash Image 81.2% Feb 2026 Official leaderboard
4 Seedream 5.0 closed weights 78.8% Official leaderboard
5 Seedream 4.0 77.8% Official leaderboard
6 GPT-Image-1.5 77.5% Official leaderboard
7 FLUX.2 [dev] 51.3% Official leaderboard
8 Qwen-Image-Edit (2511) 49.9% Official leaderboard
9 BAGEL 41.9% Official leaderboard
10 DreamOmni2 open weights 41.9% Official leaderboard
11 OmniGen2 open weights 28.6% Official leaderboard
#ModelScoreSettingDateSource
1 GPT-Image-2 88.8% Official leaderboard
2 Gemini 3.1 Flash Image 81.2% Feb 2026 Official leaderboard
3 Seedream 4.0 77.8% Official leaderboard
4 GPT-Image-1.5 77.5% Official leaderboard
5 FLUX.2 [dev] 51.3% Official leaderboard
6 Qwen-Image-Edit (2511) 49.9% Official leaderboard
7 BAGEL 41.9% Official leaderboard

Rankings by part

We read 10 parts from the benchmark’s own leaderboard in 2 groups: dimension and task. Each ranks models on one part of the test. GPT-Image-2 leads 9 of them, and GPT-Image-1.5 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Following

7 models we track have a score here.

  1. 1 GPT-Image-1.5 ↑3 90.3%
  2. 2 GPT-Image-2 ↓1 90.1%
  3. 3 Gemini 3.1 Flash Image ↓1 88%
  4. 4 Seedream 4.0 ↓1 85.3%
  5. 5 Qwen-Image-Edit (2511) ↑1 47.7%
  6. 6 FLUX.2 [dev] ↓1 46.5%
  7. 7 BAGEL 37.3%

Scores over time

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

On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Gemini 3.1 Flash Image 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Gemini 3.1 Flash Image

Source: Official MDMR-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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 9 months ago, in February 2026, for Gemini 3.1 Flash Image. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 7 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 9 months ago, in February 2026, for Gemini 3.1 Flash Image.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 81.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 7 rows for models we track and 4 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