Unverified50% confidenceFactExact time
METR evolved from the original ARC Evals team, which participated in third-party red-team evaluations of frontier models such as GPT-4 and Claude 2.
1
Sources
50%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedMetr（前身为ARC Evals）专注于前沿模型自主性与危险能力评估，曾在GPT-4和Claude 2发布前参与预发布测试73% similarUnverifiedThe AI model ecosystem has evolved from single-player dominance to a multipolar competitive landscape, with representative models including GPT-4, Claude 3, and Gemini Ultra.65% similarUnverifiedGPT-5.2 topped the ARC-AGI benchmark.65% similarUnverifiedAider is an open-source AI pair programming tool that supports connecting to multiple large model backends including GPT-4, Claude, and Gemini.64% similarUnverifiedAI model capabilities have iterated from GPT-4 to Claude 3.5 and newer versions.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/590292API
curl https://kongchang.com/api/v1/knowledge/claims/590292MCP
get_claim(id=590292)