Expired95% confidenceFactTime unknown
The evaluation used three large models as underlying engines: Claude 4.0, Claude 3.7, and Gemini Pro 2.5 0506
1
Sources
95%
Confidence
Medium-term (~90 days)
Relevance
6/2/2026
First Seen
Valid until: 8/31/2026(expired)
Sources
Deep Dive Review of AI Coding Assistants: Copilot at the Bottom — Who's the Real King?
bilibili比特光锥_BightCone
Related Entities
Related Claims
UnverifiedClaude 4.5's success rate on the Terminal Bench 2.0 benchmark is 5.1% higher than that of Gemini 3 Pro.75% similarUnverifiedThe comparison results between Claude 4.5 and Gemini 3 Pro are not one-sided, but rather each has its own strengths.74% similarUnverifiedThe four AI models tested were Claude Opus 4.5, Gemini 3 Pro, GLM 4.7, and Minimax M2.1.72% similarUnverifiedDeepSeek V4 Pro was compared horizontally against flagship models such as Gemini 5.4.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/36720API
curl https://kongchang.com/api/v1/knowledge/claims/36720MCP
get_claim(id=36720)