Benchmark Almanac

AGI-Eval Community Text to Image

Models generate images from text. The board reports objective, subjective and combined scores.

The 2026/11 leaderboard reports 18 scored model entries on its primary measure.

Released
February 2025
Kind
Image generation and editing
Level
Everyday
Scored
Graded by people
Answers
Open-ended
Tasks
Kept private
Measures
Capability
In and out
Text → Images
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Strongest model tested
Gemini 2.0 Flash Feb 2025 #147 on the capability index
Last model added
March 2025
Scores refreshed
November 21st, 2026
18
Entries on its own leaderboard, 12 models we track

Gemini 3 Pro Image Preview (nano-banana-pro) leads with 0.64 among models released by March 2025 Gemini 3 Pro Image Preview (nano-banana-pro) leads with 0.64 among models released by March 2025

Best score per entry from the benchmark's own leaderboard, read on November 21st, 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 March 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini 3 Pro Image Preview (nano-banana-pro) 0.64
  2. 2 Seedream 4.0 0.63
  3. 3 Seedream 3.0 0.61
  4. 4 GPT-4o Mar 2025 0.60
  5. 5 Z-Image-Turbo 0.60
  6. 6 Halfmoon 0.59
  7. 7 Gemini 2.5 Flash Image Preview (nano-banana) 0.59
  8. 8 FLUX1.1 [pro] 0.58
  9. 9 Seedream-2.1 0.58
  10. 10 FLUX.1 [dev] 0.57
  11. 11 HiDream-I1-Full 0.57
  12. 12 Kolors-2.0 0.57
  13. 13 Recraft V3 0.56
  14. 14 Ideogram 2.0 0.56
  15. 15 HunyuanImage 3.0 0.56
  16. 16 Wanx-2.1-Plus 0.56
  17. 17 Midjourney-6.1 0.55
  18. 18 Gemini 2.0 Flash Feb 2025 0.52

Source: Official AGI-Eval Community Text to Image leaderboard

#EntryScoreSettingDateSource
1 Gemini 3 Pro Image Preview (nano-banana-pro) 0.64 Official leaderboard
2 Seedream 4.0 0.63 Official leaderboard
3 Seedream 3.0 0.61 Official leaderboard
4 GPT-4o Mar 2025 0.60 Mar 2025 Official leaderboard
5 Z-Image-Turbo 0.60 Official leaderboard
6 Halfmoon 0.59 Official leaderboard
7 Gemini 2.5 Flash Image Preview (nano-banana) 0.59 Official leaderboard
8 FLUX1.1 [pro] 0.58 Official leaderboard
9 Seedream-2.1 0.58 Official leaderboard
10 FLUX.1 [dev] 0.57 Official leaderboard
11 HiDream-I1-Full 0.57 Official leaderboard
12 Kolors-2.0 0.57 Official leaderboard
13 Recraft V3 0.56 Official leaderboard
14 Ideogram 2.0 0.56 Official leaderboard
15 HunyuanImage 3.0 0.56 Official leaderboard
16 Wanx-2.1-Plus 0.56 Official leaderboard
17 Midjourney-6.1 0.55 Official leaderboard
18 Gemini 2.0 Flash Feb 2025 0.52 Feb 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3 Pro Image Preview (nano-banana-pro) 0.64 Official leaderboard
2 Seedream 4.0 0.63 Official leaderboard
3 Seedream 3.0 0.61 Official leaderboard
4 GPT-4o Mar 2025 0.60 Mar 2025 Official leaderboard
5 Z-Image-Turbo 0.60 Official leaderboard
6 Gemini 2.5 Flash Image Preview (nano-banana) 0.59 Official leaderboard
7 FLUX1.1 [pro] 0.58 Official leaderboard
8 FLUX.1 [dev] 0.57 Official leaderboard
9 Recraft V3 0.56 Official leaderboard
10 Ideogram 2.0 0.56 Official leaderboard
11 HunyuanImage 3.0 0.56 Official leaderboard
12 Gemini 2.0 Flash Feb 2025 0.52 Feb 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.

On the benchmark’s own leaderboard
0.52 0.54 0.56 0.58 0.60 0.62 2025 0.52 0.54 0.56 0.58 0.60 0.62 2025

Source: Official AGI-Eval Community Text to Image 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 20 months ago, in March 2025, for GPT-4o. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (18 entries).
  • Pass Models scored 12 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 20 months ago, in March 2025, for GPT-4o.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.0 Flash (#147).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on agi-eval.org: 12 rows for models we track and 6 other entries at the last read.
  • Pass Last read November 21st, 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