Unverified85% confidenceFactTime unknown

Gemini 2在Google的SWE Bench基准测试中得分80.6%

1

Sources

85%

Confidence

Medium-term (~90 days)

Relevance

5/31/2026

First Seen

Valid until: 8/29/2026

Sources

King Mode提示词：让Gemini 3.1 Pro效率提升6倍的实战指南

bilibili薛定猫AI

Related Entities

Gemini 2model Googlecompany SWE-Benchconcept

Related Claims

UnverifiedGemini 2.5 Pro在Humanities Last Exam基准测试中得分18.8%，远超O3 Mini的14%和其他模型的10%以下75% similar UnverifiedGemini 2.5 Pro从静态网页到全栈任务的得分降幅超过60%74% similar UnverifiedGemini 3.1 Pro在SWE Bench Pro上得分54.272% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/12530

API

curl https://kongchang.com/api/v1/knowledge/claims/12530

MCP

get_claim(id=12530)