reasoning benchmark
ARC-AGI v2
ARC-AGI-2 is an upgraded benchmark for measuring abstract reasoning and problem-solving abilities in AI systems through visual grid transformation tasks. It evaluates fluid intelligence via input-output grid pairs (1x1 to 30x30) using colored cells (0-9), requiring models to identify underlying transformation rules from demonstration examples and apply them to test cases. Designed to be easy for humans but challenging for AI, focusing on core cognitive abilities like spatial reasoning, pattern recognition, and compositional generalization.
Updated Aug 7, 2026
Published models16
Registry coverage16
MetricScore
EvidenceB
ARC-AGI v2 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 85.0% | 100.0% | 16 | C | |
| 2 | GO | 77.1% | 93.3% | 16 | C | |
| 3 | OP | 73.3% | 86.7% | 16 | C | |
| 4 | GO | 72.1% | 80.0% | 16 | C | |
| 5 | AN | 68.8% | 73.3% | 16 | C | |
| 6 | AN | 58.3% | 66.7% | 16 | C | |
| 7 | OP | 54.2% | 60.0% | 16 | C | |
| 8 | OP | 52.9% | 53.3% | 16 | C | |
| 9 | ME | 42.5% | 46.7% | 16 | C | |
| 10 | AN | 37.6% | 40.0% | 16 | C | |
| 11 | GO | 33.6% | 33.3% | 16 | C | |
| 12 | GO | 31.1% | 26.7% | 16 | C | |
| 13 | XA | 15.9% | 20.0% | 16 | C | |
| 14 | AN | 8.6% | 13.3% | 16 | B | |
| 15 | OP | 6.5% | 6.7% | 16 | B | |
| 16 | GO | 4.9% | 0.0% | 16 | B |
Score distribution
Top published rows on the benchmark's original scale.
ARC-AGI v2 highlights
The top published results on this benchmark's own scale.
What is ARC-AGI v2?
Definition and scoring fields from the benchmark registry.
ARC-AGI-2 is an upgraded benchmark for measuring abstract reasoning and problem-solving abilities in AI systems through visual grid transformation tasks. It evaluates fluid intelligence via input-output grid pairs (1x1 to 30x30) using colored cells (0-9), requiring models to identify underlying transformation rules from demonstration examples and apply them to test cases. Designed to be easy for humans but challenging for AI, focusing on core cognitive abilities like spatial reasoning, pattern recognition, and compositional generalization.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- ARC-AGI v2
- Modality
- multimodal
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- arc-agi-v2|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about ARC-AGI v2.
Which model scores highest on ARC-AGI v2?
GPT-5.5 is currently ranked first with 85.0%.
What does ARC-AGI v2 measure?
ARC-AGI-2 is an upgraded benchmark for measuring abstract reasoning and problem-solving abilities in AI systems through visual grid transformation tasks. It evaluates fluid intelligence via input-output grid pairs (1x1 to 30x30) using colored cells (0-9), requiring models to identify underlying transformation rules from demonstration examples and apply them to test cases. Designed to be easy for humans but challenging for AI, focusing on core cognitive abilities like spatial reasoning, pattern recognition, and compositional generalization.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
16 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.