Unverified50% confidenceFactExact time
从Claude 3 Sonnet到Claude 3.5 Sonnet再到Claude 4 Sonnet,每次升级在编码基准测试上的得分提升幅度呈递减趋势,早期版本间的跳跃可能是10-20个百分点的提升,而后续版本间的差距往往缩小到2-5个百分点
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Keyroll:一款主打稳定的Claude续杯工具深度体验
bilibili阿C技术世界6/9/2026
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%75% similarUnverifiedClaude从2.0到3.5 Sonnet的升级使其从Arena中游跃升至榜首区间75% 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% similarUnverifiedClaude Sonnet 4.6在智能体终端编码基准测试中从51%提升至59%74% similarUnverifiedClaude Sonnet 4.6在智能体工具使用测试中从43.8%提升至61.3%73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/44280API
curl https://kongchang.com/api/v1/knowledge/claims/44280MCP
get_claim(id=44280)