Verified75% confidenceBenchmarkExact time
Claude Sonnet 5.5 在终端(Terminal)基准上达到 70.6%,而上一代仅有 10.3%
5
Sources
75%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在Devin平台上使用Claude Sonnet 5,相比上一代Claude Sonnet 4.6,配额消耗大约减少30%78% similarVerifiedClaude Sonnet 5 在 SWE-bench Verified(Agentic Coding)上得分 63.22%,距 Opus 4.8 约差 6 个百分点75% similarUnverifiedSonnet 5相较Opus 4.8 Max仅便宜约72%75% similarUnverifiedClaude Sonnet 5 在 Computer Use 上得分 81.2%74% similarVerifiedSonnet 5在Terminal Bench 2.1上取得80.4%的成绩,接近Opus 4.874% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958700API
curl https://kongchang.com/api/v1/knowledge/claims/958700MCP
get_claim(id=958700)