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 · Surgical image editing

Rated on 7 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, Ideogram V4.5, Muse Image, Gemini 3.1 Flash, Nano Banana 2.1, Krea 3.

  1. 1

    Muse ImageGlif default

    Meta

    63 score out of 100

    68 overall out of 100

  2. 2

    GPT Image 2.6Glif defaultNew

    OpenAI

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

    66 overall out of 100

  3. 3

    FLUX.2 Flex

    Black Forest Labs

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

    63 overall out of 100

  4. 4

    Ideogram V4.5Glif default

    Ideogram

    69 score out of 100

    61 overall out of 100

  5. 5

    MAI Image 2.5 Generator

    Microsoft

    73 score out of 100

    61 overall out of 100

  6. 6

    Seedream 5.0 Pro

    ByteDance

    73 score out of 100

    61 overall out of 100

  7. 7

    Gemini 3.1 FlashGlif default

    Google DeepMind

    50 score out of 100

    59 overall out of 100

  8. 8

    Nano Banana 2.1Glif default

    Google DeepMind

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

    59 overall out of 100

  9. 9

    GPT Image 2.5

    OpenAI

    74 score out of 100

    58 overall out of 100

  10. 10

    Grok Imagine Image

    xAI

    32 score out of 100

    57 overall out of 100

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