Unverified70% confidenceFactTime unknown

Gemini 3.5 Flash的编码能力基准测试得分为76.2%

1

Sources

70%

Confidence

Medium-term (~90 days)

Relevance

5/31/2026

First Seen

Valid until: 8/29/2026

Sources

Gemini 3.5 Flash深度测评：Agent能力、视频生成与编码实力全面解析

bilibiliAi小舰长

Related Entities

Gemini 3.5 Flashmodel

Related Claims

UnverifiedStep 3.5 Flash在编码测试（如SWE-Bench）等特定基准测试中分数超越了Google的Gemini 3 Flash83% similar UnverifiedGemini 3.5 Flash在Agent任务基准测试中获得83.6%的得分83% similar VerifiedGemini 3.5 Flash在几乎所有基准测试中超越了Gemini 3.1 Pro82% similar UnverifiedGemini 3.5 Flash支持1,048,576个输入token和65,536个最大输出token82% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/14202

API

curl https://kongchang.com/api/v1/knowledge/claims/14202

MCP

get_claim(id=14202)