Skip to main content

Benchmark profile

ARC-AGI-1 Semi-Private Evaluation (ARC-AGI-1)

ARC Prize fluid-intelligence benchmark using novel visual grid transformations.

Data verified

Benchmark score on ARC-AGI-1 — July 24, 2026

BenchLM mirrors the published score view for ARC-AGI-1. Claude Opus 5 leads the public snapshot at 97.50%. BenchLM does not use these results to rank models overall.

1 modelReasoningCurrentDisplay onlyUpdated July 24, 2026

Benchmark score table (1 model)

Score
1
Claude Opus 5Anthropic · Closed
97.50%

About ARC-AGI-1

Year

2026

Tasks

Semi-private ARC-AGI-1 evaluation set

Format

Verified accuracy

Difficulty

Abstract visual reasoning

The Opus 5 system card reports the ARC Prize Foundation's verified semi-private max-effort result.

BenchLM freshness & provenance

Version

ARC-AGI-1 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does ARC-AGI-1 measure?

ARC Prize fluid-intelligence benchmark using novel visual grid transformations.

Which model scores highest on ARC-AGI-1?

Claude Opus 5 by Anthropic currently leads with a score of 97.50% on ARC-AGI-1.

How many models are evaluated on ARC-AGI-1?

1 AI models have been evaluated on ARC-AGI-1 on BenchLM.

Last updated: July 24, 2026 · BenchLM version ARC-AGI-1 2026