reasoning benchmark
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.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
Arc Ranking
Higher score ranks better on this benchmark.
| 01 | GO | 2.5% | 100.0% | 1 | C |
Arc Highlights
The leading models and scores on this benchmark.
What is Arc?
What Arc measures and how its scores work.
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.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Arc
- Modality
- multimodal
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- arc|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Arc.
Which model scores highest on Arc?
Gemini 2.5 Flash-Lite is currently ranked first with 2.5%.
What does Arc measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.