Unverified50% confidenceBenchmarkExact time
When looking only at LLM judgment (scored using GPT-5.5), the evaluator tended to dislike Grok, favor Claude Opus and Sonnet, and dislike GPT-5.6.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/23/2026
First Seen
Valid until: 12/22/2026
Sources
Related Entities
Related Claims
UnverifiedPromotional copy claims that Grok 4.6 performance crushes GPT-5.6 and Claude, but such absolute statements lack publicly reproducible benchmark test support68% similarUnverifiedWill Depue, a former OpenAI researcher, commented that GPT-5.5 loses to Claude in terms of 'human feel,' and the comment received tens of thousands of likes.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942367API
curl https://kongchang.com/api/v1/knowledge/claims/942367MCP
get_claim(id=942367)