Arc
The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to measure human-like general fluid intelligence through grid-based reasoning tasks. It consists of 800 tasks (400 training, 400 evaluation) where each task presents input-output grids that require understanding abstract patterns and transformations. Test-takers must produce exactly correct output grids for all test inputs in a task to solve it, with 3 trials allowed per test input. ARC aims to enable fair comparisons of general intelligence between AI systems and humans using priors designed to be as close as possible to innate human priors.
Gemini 2.5 Flash-Lite from Google currently leads the Arc leaderboard with a score of 0.025 across 1 evaluated AI models.
Gemini 2.5 Flash-Lite leads with 2.5%.
Progress Over Time
Interactive timeline showing model performance evolution on Arc
Arc Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Google | — | — | — |
FAQ
Common questions about Arc.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions