Expired80% confidenceFactTime unknown
In 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.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe combined results of five benchmark tests constitute a technical tie, with Claude 4.5 leading in practical programming and Gemini 3 Pro leading in knowledge reasoning.81% similarUnverifiedGemini 2.5 Pro支持100万token上下文窗口，在多项基准测试中表现优异，尤其在长上下文理解和多步推理方面领先78% similarVerifiedGemini 2.5 Pro ranks among the top performers on multiple authoritative benchmarks including MMLU, HumanEval, and MATH.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/18601API
curl https://kongchang.com/api/v1/knowledge/claims/18601MCP
get_claim(id=18601)