Expired60% confidenceFactTime unknown
The code also mentions a model called 'King4,' which reportedly demonstrated strong performance in early testing; it is unclear whether it is an early version of Gemini 3 or a variant of Gemini 2.5 Pro equipped with a Deep Think feature.
1
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedGemini 3 significantly outperforms comparable models on the SWE-bench benchmark in agentic scenarios.77% similarUnverifiedDeepSeek V4 Pro was compared horizontally against flagship models such as Gemini 5.4.76% similarUnverifiedIn graduate-level reasoning and Agent tool-use benchmarks, Opus 4 is largely in the lead, though Gemini 2.5 Pro comes very close on some items.75% similarUnverifiedGemini 2.5 Pro (version 0325) is positioned as a model built for complex tasks with exceptional reasoning capabilities.74% similarUnverifiedGemini 2.5 Pro is on par with O3 Mini in math capability benchmarks, with both leaving all other models far behind.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/25366API
curl https://kongchang.com/api/v1/knowledge/claims/25366MCP
get_claim(id=25366)