reasoning benchmark
ArcAGI2
ARC-AGI-2 is the second-generation Abstraction and Reasoning Corpus benchmark measuring fluid, general reasoning and abstraction.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
ArcAGI2 Ranking
Higher score ranks better on this benchmark.
| 01 | BY | 62.5% | 100.0% | 2 | C | |
| 02 | BY | 61.3% | 0.0% | 2 | C |
ArcAGI2 Score Distribution
A closer view of the leading scores on this benchmark.
ArcAGI2 Highlights
The leading models and scores on this benchmark.
What is ArcAGI2?
What ArcAGI2 measures and how its scores work.
ARC-AGI-2 is the second-generation Abstraction and Reasoning Corpus benchmark measuring fluid, general reasoning and abstraction.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ArcAGI2
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- arcagi2|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ArcAGI2.
Which model scores highest on ArcAGI2?
Seed 2.1 Pro is currently ranked first with 62.5%.
What does ArcAGI2 measure?
ARC-AGI-2 is the second-generation Abstraction and Reasoning Corpus benchmark measuring fluid, general reasoning and abstraction.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.