// BENCHMARK

ARC-AGI-2 (Private) benchmark

AI model leaderboard for the ARC-AGI-2 (Private) benchmark. Compare how large language models score on ARC-AGI-2 (Private), see the full ranking, and understand what this AI benchmark measures. Private/holdout split of ARC-AGI-2 — used for system-card evaluations.

Leaderboard

No model scores reported yet.

Frequently asked questions about ARC-AGI-2 (Private)

What is the ARC-AGI-2 (Private) benchmark?

Private/holdout split of ARC-AGI-2 — used for system-card evaluations.

How is the ARC-AGI-2 (Private) benchmark scored?

ARC-AGI-2 (Private) is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on ARC-AGI-2 (Private)?

No model scores have been reported for ARC-AGI-2 (Private) yet. Check back as the leaderboard is updated.

Is a higher ARC-AGI-2 (Private) score better?

Yes. On ARC-AGI-2 (Private) a higher score indicates better performance, so models near the top of the leaderboard are the strongest.