Unverified50% confidenceFactExact time
Artificial Analysis Intelligence Index V5 builds the evaluation weight of 60 percentage points on private test sets or hidden answers for the first time.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Google's Gemini 4 Carbon Tops the Rankings, Anthropic Achieves First Quarterly Profit
bilibiliodOObo10/28/2026
Related Entities
Related Claims
UnverifiedAbout 60% of the index scores in v5 come from evaluations using private test sets or withheld answers, and external researchers cannot reproduce these results.79% similarUnverifiedThe overall accuracy remains at just above 60%, indicating that automated annotation is still far from fully replacing human labor.69% similarUnverifiedEven when the correct value was retrieved, agents acted on it only 55% of the time, exposing a gap between retrieving information and acting on it.69% similarUnverifiedAudit data shows that articles cited by AI had an average quality score of 60.4, while articles not cited scored 62.5.69% similarUnverifiedCarbon scored 59 on the Artificial Analysis Intelligence Index 5.00, ranking first globally.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111538API
curl https://kongchang.com/api/v1/knowledge/claims/1111538MCP
get_claim(id=1111538)