Unverified50% confidenceBenchmarkExact time
ARC-AGI is a benchmark test that requires inferring abstract rules from very few examples.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThis test specifically examines a model's ability to abstract general patterns from limited samples (generalizing from a few examples).66% similarUnverifiedBenchmarks that currently receive more attention for evaluating AGI reasoning capabilities include ARC (Abstraction and Reasoning Corpus) and BIG-Bench Hard.66% similarUnverifiedARC-AGI contains 400 training problems and 400 test problems, with each problem consisting of 2–3 input-output examples and one test case to be solved.66% similarVerifiedARC-AGI is a benchmark designed by AI safety researcher François Chollet specifically to measure fluid intelligence.62% similarUnverifiedHaving AI generate corresponding unit tests and actually running them is the minimum requirement for validating vibe-coded code.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/950705API
curl https://kongchang.com/api/v1/knowledge/claims/950705MCP
get_claim(id=950705)