Unverified80% confidenceFactTime unknown

在研究生级推理和Agent工具使用基准测试中，Opus 4基本处于领先地位，但Gemini 2.5 Pro在部分项目上与之非常接近

1

Sources

80%

Confidence

Medium-term (~90 days)

Relevance

6/1/2026

First Seen

Valid until: 8/30/2026

Sources

Claude 4实测：Opus 4与Sonnet 4深度评测对比

bilibili智译工坊

Related Entities

Claude Opus 4model Gemini 2.5 Promodel

Related Claims

Unverified五项基准测试综合结果为技术性平局，Claude 4.5在编程实战领先，Gemini 3 Pro在知识推理领先81% similar UnverifiedGemini 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% similar VerifiedGemini 2.5 Pro在MMLU、HumanEval、MATH等多项权威基准测试中位居前列77% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/18601

API

curl https://kongchang.com/api/v1/knowledge/claims/18601

MCP

get_claim(id=18601)