Unverified50% confidenceBenchmarkExact time
Sonnet 5在GDP EVOL基准上达到16.19%,反超了Opus
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/6/2026
First Seen
Valid until: 10/4/2026
Sources
Claude Sonnet 5实测:隐藏的Token陷阱让「低价」成幻觉
bilibili浮生千山路w6/30/2026
Related Claims
UnverifiedClaude Sonnet 4.6在GDPVal AA基准测试中得分超过了Opus 4.677% similarUnverifiedClaude Sonnet 5在Terminal 2.1得分80.4,计算机使用得分81.2,GDP评估达1619并超越OPUS76% similarUnverifiedSonnet 5相较Opus 4.8 Max仅便宜约72%72% similarUnverifiedClaude Sonnet 5 在 GDP-WoW 基准上得 1619 分,反超 Opus71% similarVerifiedSonnet 5在Terminal Bench 2.1上取得80.4%的成绩,接近Opus 4.870% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/113229API
curl https://kongchang.com/api/v1/knowledge/claims/113229MCP
get_claim(id=113229)