ARC-AGI-3
Progress Over Time
Interactive timeline showing model performance evolution on ARC-AGI-3
ARC-AGI-3 Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Anthropic | — | 1.0M | $5.00 / $25.00 | ||
| 2 |  OpenAI | — | 1.1M | $5.00 / $30.00 | ||
| 3 | OpenAI | — | 1.1M | $2.00 / $12.00 | ||
| 4 | OpenAI | — | 1.1M | $0.20 / $1.20 |
What is ARC-AGI-3?
ARC-AGI-3 is the third-generation Abstraction and Reasoning Corpus benchmark, an interactive-reasoning evaluation designed to measure fluid, novel problem-solving ability that remains far from saturated for frontier models.
ARC-AGI-3 is a multimodal benchmark evaluating models on reasoning and general tasks. LLM Stats tracks 4 models on this benchmark, scored on a 0–1 scale. The current average is 0.1, with the leader at 0.3.
Compare leaders on the best AI for reasoning and best AI for general leaderboards.
Current leaders
Claude Opus 5 from Anthropic currently leads the ARC-AGI-3 leaderboard with a score of 0.302 across 4 evaluated AI models.
FAQ
Common questions about the ARC-AGI-3 benchmark and leaderboard.