Model leaderboard

Every model runs the same Glif Standard Tests. Scores combine expert human reviewers, expert AI judges and votes from the wider community, and we rank models on quality, speed and cost.

Image · Character consistency

Rated on 10 tests.

Score (50 is average)

Credits per run, log scale

Higher scores are better; further left is cheaper. Highlighted are the Glif defaults: GPT Image 2.6, Muse Image, Gemini 3.1 Flash, Nano Banana 2.1, Krea 3, Ideogram V4.5.

1
Muse ImageGlif default
Meta
20s, typical wait
$
76 score out of 100
77 overall out of 100
2
GPT Image 2.6Glif defaultNew
OpenAI
18s, typical wait
$$$
83 score out of 100, early score: expect it to move
68 overall out of 100
3
Grok Imagine Image
xAI
11s, typical wait
$
50 score out of 100
68 overall out of 100
4
Gemini 3.1 FlashGlif default
Google DeepMind
11s, typical wait
$$
60 score out of 100
65 overall out of 100
5
Nano Banana 2.1Glif default
Google DeepMind
16s, typical wait
$$
57 score out of 100, early score: expect it to move
63 overall out of 100
6
Phota Image Editor
17s, typical wait
$$
61 score out of 100
60 overall out of 100
7
Nano Banana Pro
Google DeepMind
19s, typical wait
$$$
64 score out of 100
57 overall out of 100
8
Seedream 5.0 Pro
ByteDance
36s, typical wait
$$
67 score out of 100
57 overall out of 100
9
GPT Image 2.5
OpenAI
26s, typical wait
$$$
69 score out of 100
55 overall out of 100
10
FLUX.2 Pro
Black Forest Labs
14s, typical wait
$$$
43 score out of 100
51 overall out of 100

* Early score: not enough ratings yet, so expect it to move.