Unverified60% confidenceFactTime unknown

Gemini 3.1 Pro在SWE Bench Pro上得分54.2

2

Sources

60%

Confidence

Medium-term (~90 days)

Relevance

5/31/2026

First Seen

Valid until: 8/29/2026

Sources

Claude Opus 4.7深度实测：编码能力飙升，最强模型Mythos仍被封印

bilibili枫叶边城

Related Entities

Gemini 3.1 Promodel SWE Bench Proconcept

Related Claims

UnverifiedClaude 4.5在Terminal Bench 2.0测试中成功率高出Gemini 3 Pro 5.1%79% similar Unverified在SimpleQA评测中，Gemini 3.1 Pro以75.6分领先，DeepSeek V4 Pro得分57.9分77% similar UnverifiedGemini 3.5 Pro在ARC-AGI-2通用智能评估中得分42分，远超同期竞品76% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/13840

API

curl https://kongchang.com/api/v1/knowledge/claims/13840

MCP

get_claim(id=13840)