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.

Video · Multi-image reference

Rated on 1 test.

Score (50 is average)
Credits per run, log scale
Higher scores are better; further left is cheaper. Highlighted are the Glif defaults: Hailuo H3 Max (MiniMax).

  1. 1

    Grok Imagine · Reference to video

    xAI

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

    81 overall out of 100

  2. 2

    Gemini Omni Flash 1.1 · Reference to video

    Google DeepMind

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

    60 overall out of 100

  3. 3

    Seedance 2.0 Fast Reference

    ByteDance

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

    58 overall out of 100

  4. 4

    Hailuo H3 Max (MiniMax)Glif default

    MiniMax

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

    54 overall out of 100

  5. 5

    Seedance 2.0 Mini Reference

    ByteDance

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

    51 overall out of 100

  6. 6

    Wan 3.0 Reference

    Alibaba Cloud

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

    41 overall out of 100

  7. 7

    Kling 4.0 · Reference to video

    Kuaishou Technology

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

    38 overall out of 100

  8. 8

    Seedance 2.0 Reference

    ByteDance

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

    35 overall out of 100

  9. 9

    Seedance 2.5 Reference

    ByteDance

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

    30 overall out of 100

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