Verified75% confidenceFactTime unknown
Composer 2.5在Cursor Bench V3.1上得分63.2%，Opus 4.7在默认配置下为61.6%，GPT 5.5为59.2%
5
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Cursor Composer 2.5深度解析：开源模型1/10成本叫板Claude 4.7
bilibili拿幸AI启示录
Related Entities
Related Claims
Unverified在Terminal Bench 2.0基准测试中，Composer 2得分为61.7%77% similarVerified在Terminal Bench 2.0测试中，K2.6打出66.7分，比GPT-5.4和Claude Opus 4.6都略高75% 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%73% similarUnverifiedTerminal Bench 2.1测试中GPT-5.6 Ultra得分接近92%，Fable 5为88%，考虑误差范围基本持平71% similarUnverified在SWE-Bench Pro编程评测上，Claude Fable 5以80%的成绩领先GPT-5.6 Sol的64.6%71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/12638API
curl https://kongchang.com/api/v1/knowledge/claims/12638MCP
get_claim(id=12638)