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 · Text-to-image

Rated on 20 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, Nano Banana 2.1, Gemini 3.1 Flash, Muse Image, Ideogram V4.5, Krea 3.

  1. 1

    Nano Banana 2.1Glif default

    Google DeepMind

    79 score out of 100, early score: expect it to move

    76 overall out of 100

  2. 2

    GPT Image 2.6Glif defaultNew

    OpenAI

    85 score out of 100, early score: expect it to move

    70 overall out of 100

  3. 3

    GPT Image 2.5

    OpenAI

    86 score out of 100

    66 overall out of 100

  4. 4

    Gemini 3.1 FlashGlif default

    Google DeepMind

    62 score out of 100

    66 overall out of 100

  5. 5

    Muse ImageGlif default

    Meta

    49 score out of 100

    61 overall out of 100

  6. 6

    Nano Banana Pro

    Google DeepMind

    65 score out of 100

    59 overall out of 100

  7. 7

    FLUX.2 Pro

    Black Forest Labs

    55 score out of 100

    58 overall out of 100

  8. 8

    Seedream 5.0 Pro

    ByteDance

    63 score out of 100

    55 overall out of 100

  9. 9

    Grok Imagine Image

    xAI

    22 score out of 100

    51 overall out of 100

  10. 10

    Ideogram V4.5Glif default

    Ideogram

    49 score out of 100

    49 overall out of 100

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