evals.report
BenchmarksLabsCompareRun guidesIn the wild
BenchmarksReasoning

ARC-AGI-3

The interactive ARC-AGI-3 generalization benchmark: agents must learn novel game environments from scratch (semi-private set).

ReasoningaccuracyHigher is better

What this benchmark measures

The interactive ARC-AGI-3 generalization benchmark: agents must learn novel game environments from scratch (semi-private set).

Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.

The metric shown here is accuracy. It should be interpreted within ARC-AGI-3, not compared as part of a site-wide ranking.

What to be careful about

Competition submissions and private/evaluation splits make provenance important.

No composite ranking
evals.report never combines benchmarks. accuracy on ARC-AGI-3 is its own number — don’t average it with other metrics.

Frequently asked

What is ARC-AGI-3?

The interactive ARC-AGI-3 generalization benchmark: agents must learn novel game environments from scratch (semi-private set). It is a reasoning benchmark measured by accuracy.

What does accuracy mean on ARC-AGI-3?

ARC-AGI-3 reports accuracy (%); higher is better. Scores are shown only within ARC-AGI-3 and are never averaged with other benchmarks.

What is the top reported ARC-AGI-3 score?

GPT-5.6 Sol has the top reported score on ARC-AGI-3: 7.78% (accuracy).

Why do ARC-AGI-3 scores differ across runs?

Harness, scaffold, reasoning effort, and prompt setup change results, so two runs of the same model can differ. evals.report keeps each score with its run context so the differences stay visible.

Does evals.report rank models across benchmarks?

No. ARC-AGI-3 scores are shown within their own metric; evals.report never combines benchmarks into a composite ranking or a single "best model".