Verified80% confidenceFactTime unknown

Claude 3.5 Sonnet在多项基准测试中与GPT-4o不相上下

8

Sources

80%

Confidence

Medium-term (~90 days)

Relevance

6/1/2026

First Seen

Valid until: 8/30/2026

Sources

Anthropic官方Agent构建指南：工作流vs智能体选型全解析

bilibili慢学AI

Related Entities

Claude 3.5 Sonnetmodel GPT-4omodel

Related Claims

UnverifiedClaude Sonnet 4在GPT-5.6 Pro之前上线发布80% similar Unverified早期GPT-3的HumanEval Pass@1不足10%，而GPT-4o、Claude 3.5 Sonnet等顶尖模型已稳定超过85%78% similar UnverifiedClaude Sonnet 4的总耗时大约是GPT-5的四倍78% similar UnverifiedClaude Sonnet 4.6的价格仅为GPT-4的十分之一77% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/21730

API

curl https://kongchang.com/api/v1/knowledge/claims/21730

MCP

get_claim(id=21730)