Unverified60% confidenceBenchmarkExact time
Claude 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OPUS
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026
Sources
Related Claims
UnverifiedClaude Sonnet 5 在 Computer Use 上得分 81.2%82% similarUnverifiedClaude Sonnet 4.6在GDPVal AA基准测试中得分超过了Opus 4.679% similarUnverifiedClaude Sonnet 5 在 GDP-WoW 基准上得 1619 分,反超 Opus78% similarUnverified测试中GLM 5.1综合得分89.3分,排名第一,超过Claude Sonnet 4.6的87.2分77% similarUnverifiedSonnet 5在GDP EVOL基准上达到16.19%,反超了Opus76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/589913API
curl https://kongchang.com/api/v1/knowledge/claims/589913MCP
get_claim(id=589913)