Unverified85% confidenceFactTime unknown
Qwen3.6 35B在SWE Bench Verified上的成绩距离Claude Opus 4.6仅差1.6个百分点
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026
Sources
Qwen3.6 35B开源实测逼近Claude，xAI语音克隆API正式上线
bilibili硅基米德AI
Related Entities
Related Claims
UnverifiedQwen3.5在IFBench指令遵循评测中得分76.5，超过GPT-5.2的75.4和Claude 4.5 Opus的5877% similarUnverified在终端基准（Terminal Bench）测试中，Qwen 3.6 27B得分约60.7，而Muse Glimmer只有51.7，明显落后77% similarUnverified在SWE Bench Verified榜单上，Qwen3.6 35B取得了73.4%的成绩77% similarUnverifiedQwen3.6 27B 在 SWE-bench Verified 上拿到77.2分76% similarUnverifiedQwen3.6 27B Q4量化版总分650分，排名第四74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/17985API
curl https://kongchang.com/api/v1/knowledge/claims/17985MCP
get_claim(id=17985)