[KongchangAI]
Unverified50% confidenceBenchmarkExact time

The MATH benchmark was created by Dan Hendrycks's team at UC Berkeley and covers 7 areas including algebra, geometry, number theory, probability, and combinatorics, comprising 12,500 problems ranging in difficulty from AMC10 to AIME level.

1
Sources
50%
Confidence
Long-term
Relevance
8/8/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/706718
API
curl https://kongchang.com/api/v1/knowledge/claims/706718
MCP
get_claim(id=706718)