Unverified50% confidenceFactExact time
ARC (Abstraction and Reasoning Corpus) was proposed by François Chollet in 2019 and was specifically designed to test fluid intelligence, requiring the induction of rules from very few examples and their application to new instances.
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedFrançois Chollet emphasizes abstract reasoning and generalization ability, and proposed the ARC benchmark as a measure of these capabilities.79% similarVerifiedARC-AGI is a benchmark designed by AI safety researcher François Chollet specifically to measure fluid intelligence.72% similarUnverifiedARC-AGI is a general intelligence benchmark designed by Kaggle founder François Chollet, with human-level performance typically above 85%.67% similarUnverifiedARC-AGI is a benchmark test that requires inferring abstract rules from very few examples.65% similarUnverifiedBenchmarks that currently receive more attention for evaluating AGI reasoning capabilities include ARC (Abstraction and Reasoning Corpus) and BIG-Bench Hard.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980200API
curl https://kongchang.com/api/v1/knowledge/claims/980200MCP
get_claim(id=980200)