Unverified50% confidenceOpinionExact time
评测者认为通义千问3.6 27B是30B级别中对高考数学题表现最好的模型
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/18/2026
First Seen
Valid until: 11/16/2026
Sources
Related Claims
Unverified本次评测使用全国一卷高考数学题对比Muse Glimmer和通义千问3.6 27B76% similarUnverifiedThe tester estimated that Codex can complete approximately 30% of the tasks on the kanban board.70% similarUnverified通义千问3.6 27B在语义三次全对率和格式正确率上均领先Muse Glimmer70% similarUnverifiedQwen3.6-27B's benchmark scores place it at the leading position among models of similar scale (20B–30B parameter range).68% similarUnverified测试者Luke认为Qwen3 27B是他测试过的在本地运行的最强编程模型63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/767869API
curl https://kongchang.com/api/v1/knowledge/claims/767869MCP
get_claim(id=767869)