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 · Multi-image reference

Rated on 2 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, Krea 3, Ideogram V4.5.

  1. 1

    Nano Banana 2.1Glif default

    Google DeepMind

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

    70 overall out of 100

  2. 2

    Gemini 3.1 FlashGlif default

    Google DeepMind

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

    69 overall out of 100

  3. 3

    Phota Image Editor

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

    69 overall out of 100

  4. 4

    GPT Image 2.6Glif defaultNew

    OpenAI

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

    66 overall out of 100

  5. 5

    Muse ImageGlif default

    Meta

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

    61 overall out of 100

  6. 6

    FLUX.2 Pro

    Black Forest Labs

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

    59 overall out of 100

  7. 7

    Seedream 5.0 Pro

    ByteDance

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

    57 overall out of 100

  8. 8

    Seedream 5.0 Lite

    ByteDance

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

    55 overall out of 100

  9. 9

    GPT Image 2.5

    OpenAI

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

    54 overall out of 100

  10. 10

    Nano Banana Pro

    Google DeepMind

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

    47 overall out of 100

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