Unverified75% confidenceFactTime unknown
Opus 4在SWE-bench Verified上的通过率超过72%,显著领先于其他竞争模型
1
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026
Sources
Claude Code用不了?Cursor和Windsurf接入Opus 4替代方案实测
bilibili杭州黄老师
Related Entities
Related Claims
VerifiedClaude 4.5 Opus 在 SWE-Bench Verified 上达到了 80.9% 的成绩79% similarUnverifiedOpus 4.6在OS World Verified基准测试中得分72.7%79% similarUnverifiedClaude Opus 4.8在智能体实战跑分中拿下1890分,比上一代高出137分,甩开GPT 5.5达121分74% similarUnverifiedClaude Opus 4.8 scored 69.2% on SWEBench Pro, up from Opus 4.7's 64.3%74% similarUnverifiedClaude Opus 4.6在SWE-Bench Pro测试中得分为53.4%73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/20771API
curl https://kongchang.com/api/v1/knowledge/claims/20771MCP
get_claim(id=20771)