Expired60% confidenceBenchmarkExact time
Alibaba Cloud's Qwen2.5-Coder-32B surpassed GPT-4o on mainstream code benchmarks including HumanEval and MBPP in evaluations conducted at the end of 2024.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/16/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/14/2026(expired)
Sources
Related Claims
UnverifiedThe Qwen2.5-Coder series is produced by Alibaba's Tongyi Lab, and its 32B parameter version surpasses GPT-4o on multiple metrics.82% similarUnverifiedAccording to the SWE-Bench Verified benchmark, Qwen 2.5 Coder 32B achieves a coding ability score of 61.771% similarUnverifiedBenchmarked against Qwen3.8-27B, Agens Volundr 32B leads on LiveCodeBench v6 (+4.2), HumanEval (+4.3), AIME 2025 (+2.9), and MATH-500 (+1.6).70% similarUnverifiedGPT-4o and Qwen 2.5 Coder 32B tied for second place in DataBugBench, both scoring 4/5 with an accuracy of 80%.70% similarUnverified智谱GLM-4系列在HumanEval、MBPP等代码基准测试中达到国际第一梯队水平69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/531174API
curl https://kongchang.com/api/v1/knowledge/claims/531174MCP
get_claim(id=531174)