Expired90% confidenceEventTime unknown
In a complex task test involving the generation of a visualization HTML for six sorting algorithms, Gemini 3.1 and Qwen 3.5 400B succeeded, while the local version of QwenCoder 80B failed.
1
Sources
90%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedQwen3 8B版本在工具调用（Function Calling）基准测试中表现突出72% similarUnverifiedQwen3.6 27B NVFP4 achieved a perfect score of 100 in the tool-calling (ToolCore) test.69% similarUnverifiedThe original Qwen3.6 27B Q4 scored 97 in the tool-calling test, demonstrating that distillation does not always improve performance.68% similarUnverifiedAlibaba released a preview of Qwen 3.6 MAX, which outperformed Claude 4.5 Opus and GLM 5.1 on coding tests including SWE Bench Pro and Terminal Bench; it is currently a closed-source model accessible only via Alibaba Cloud API or Qwen Studio.68% similarUnverifiedThe Qwen2.5-Coder series is produced by Alibaba's Tongyi Lab, and its 32B parameter version surpasses GPT-4o on multiple metrics.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16885API
curl https://kongchang.com/api/v1/knowledge/claims/16885MCP
get_claim(id=16885)