aiaimodel.cards
← All benchmarks

ARC-AGI-3

Abstract visual reasoning puzzles that test learning new rules from a few examples.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Claude Opus 5 · Anthropicbest value
    30.2%

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • Claude Opus 5 Table 8.1.A, p.148–149

    Claude Opus 5 results use adaptive thinking at max effort, averaged over five trials (ARC-AGI-3 at high effort). GPT-5.6 Sol's FrontierBench figure uses Codex and its ARC-AGI-1 figure is at xhigh. The Fable 5 HealthBench Professional figure carries a footnote reading "Mythos 5". Competitor figures come from the developers' own published results or leaderboards.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.