Skip to content
BetaBenchAlert v0.1 is in Beta.Numbers are real, but pages and rules can still change.See what changed

Live board

Models

The 4 models we lead with, ranked by typical total wait after at least 12 completed checks. Every other pin lives on Other models.

Typical total wait

The models we lead with

Each lab’s best model, plus Opus 5. Ranked by typical total wait on our machine; writing speed sits beside it.

  1. 1st place

    Grok 4.6Fastest

    grok-4.6 · xhigh

    6.46s

    total wait

    37.0 answer tok/s

    Sets the pace

  2. 2nd place

    Opus 5

    claude-opus-5 · high

    7.21s

    total wait

    33.5 answer tok/s

    12% longer wait

  3. 3rd place

    Fable 5rate limit warning

    claude-fable-5 · high

    7.90s

    total wait

    30.5 answer tok/s

    22% longer wait

  4. 4th place

    GPT-5.6 Solfailed

    gpt-5.6-sol · high

    11.3s

    total wait

    21.5 answer tok/s

    75% longer wait

Other modelsHaiku 4.5, Sonnet 5, GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.5, and Grok 4.5. Same tests, every round. They are not on the home boards.6 pinned models

Read next

How to read this

An empty typical result means the model has fewer than 12 completed checks in the window. It never means zero, and it never means broken.