Unverified50% confidenceBenchmarkExact time
On the ARC-AGI-2 benchmark, Meta^n is the only method to score above zero.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedAdam的一阶矩衰减系数β₁通常默认为0.970% similarUnverifiedThe AI field commonly uses continuous values from 0 to 1 for scoring, and can also use the two discrete values 0 and 1 to represent the traditional fail and perfect score.66% similarUnverifiedOn the ARC-AGI-3 benchmark, GPT-5.6 Sol scored 8%, while most other models scored below 2%; Anthropic did not run Fable due to prohibitively high costs.64% similarUnverified1个基点等于0.01个百分点63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/911651API
curl https://kongchang.com/api/v1/knowledge/claims/911651MCP
get_claim(id=911651)