LLM Reference
activeReasoning

ARC Prize / ARC Challenge

Metric: ARC-AGI ScoreIntroduced: 2019

Abstraction and Reasoning Corpus (ARC-AGI) with visual grid puzzles testing core reasoning and novel problem-solving. ARC Prize 2024-2025 competitions track annual progress.

Models ranked

2

tracked on this benchmark

Score band

77.1 – 73.3

best → lowest tracked

Snapshot trend

need ≥2 snapshots

Leaderboard

Tracked models ranked by ARC-AGI Score (higher is better).

Compare candidates
#Model variant and provenanceScore
1
Gemini 3.1 Pro Preview
Version: ARC-AGI-2Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
77.1
2
GPT-5.4
Version: ARC-AGI-2Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
73.3

How to read this benchmark

This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.

Trust this score when

  • There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
  • The model list covers the same version family you can actually deploy today.
  • Top candidates overlap with your required routing and feature requirements.

Be cautious when

  • There is only one benchmark snapshot or the dataset appears stale.
  • The benchmark metric direction is opposite of your decision objective.
  • The score difference between options is narrow and likely within implementation variance.

Related benchmarks

Last reviewed: Jun 7, 2026