Unverified50% confidenceBenchmarkExact time
根据SWE-Bench Verified基准测试,Qwen 2.5 Coder 32B的编码能力评分达到61.7分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedQwen2.5-Coder 系列由阿里巴巴通义实验室出品,其32B参数版本在多项指标上超越了GPT-4o76% similarVerifiedQwen3.6 27B 在 SWE-bench Verified 上拿到77.2分75% similarUnverified阿里云Qwen2.5-Coder-32B在2024年底的评测中,在HumanEval、MBPP等主流代码基准上超越GPT-4o71% similarUnverifiedQwen2.5-Coder和DeepSeek-Coder-V2在HumanEval、MBPP等代码基准测试中的表现已非常接近Claude 3.5 Sonnet等顶级闭源模型71% similarUnverified通过在约3000条浏览器操作轨迹上微调Qwen3.5-4B,开发者将BrowseWebApp Bench基准测试的准确率从22%提升至63%70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/904295API
curl https://kongchang.com/api/v1/knowledge/claims/904295MCP
get_claim(id=904295)