Model leaderboard
Every model runs the same Glif tests. Scores come from 2,042 blind votes by 10 Glif team members, plus 1,279 AI judge scores, each counting as half a vote. Each kind of task has its own board.
Score out of 100: how often people would pick this model's output over an average model's on the same tests. 50 is average.
How we score
Every model runs the same Glif tests. Team members see two outputs side by side without the model names and pick the one that better fits the test, or call it a tie. An AI judge also scores every output from 0 to 10.
A Bradley-Terry fit turns all those head-to-head results into one rating per model. Ties count as half a win, and each AI judge score counts as half a vote.
The score is the predicted chance people prefer this model's output to the average model's on the same board, so 50 is average. A board is one kind of task, like text-to-image. Scores only compare models on the same board.
The 90% range comes from resampling the votes and refitting many times. Overlapping ranges are close to a tie. A model ranks once it has 20 votes' worth of ratings on a board. Until then it shows no score, only how close it is.
Bars show each score’s 90% range. Overlapping bars are close to a tie.
Show vote countsImage · Character consistency
471 team votes on 10 tests. A model ranks once it has 20 votes’ worth of ratings here.
1
Muse ImageGlif default
78 out of 100, 90% range 72 to 84
2
GPT Image 2.5Glif default
73 out of 100, 90% range 68 to 80
3
FLUX 3 Image
72 out of 100, 90% range 63 to 81
4
Seedream 5.0 Pro
72 out of 100, 90% range 64 to 80
5
Nano Banana Pro
65 out of 100, 90% range 59 to 74
6
Nano Banana 2.1Glif default
65 out of 100, 90% range 52 to 75
7
Gemini 3.1 FlashGlif default
60 out of 100, 90% range 49 to 70
8
Phota Image Editor
59 out of 100, 90% range 50 to 68
9
Krea 3Glif default
52 out of 100, 90% range 39 to 62
10
Grok Imagine Image
51 out of 100, 90% range 42 to 59
11
Seedream V4.5
47 out of 100, 90% range 36 to 59
12
Ideogram V4.5Glif default
45 out of 100, 90% range 35 to 52
13
FLUX.2 Pro
43 out of 100, 90% range 34 to 54
14
Seedream 5.0 Lite
41 out of 100, 90% range 31 to 50
15
FLUX.2 Flex
32 out of 100, 90% range 23 to 42