Unverified85% confidenceFactTime unknown
Opus 4.6在OS World Verified基准测试中得分72.7%
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Claude Sonnet 4.6评测:十分之一价格实现旗舰级AI性能
bilibili乱砍一通
Related Entities
Related Claims
UnverifiedOpus 4在SWE-bench Verified上的通过率超过72%,显著领先于其他竞争模型79% similarPartially VerifiedClaude Opus 4.8在SWE-bench基准测试中得分69.2%,GPT 5.5为58.6%,Google Gemini为54.2%76% similarUnverifiedSonnet 4.6在OS World Verified基准测试中得分72.5%74% similarUnverifiedClaude Opus 4.6在SWE-Bench Pro测试中得分为53.4%72% similarUnverifiedClaude Opus 4.7中间检查点通过率达57%,最终准确率却只有39.8%71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13716API
curl https://kongchang.com/api/v1/knowledge/claims/13716MCP
get_claim(id=13716)