Unverified50% confidenceEventTime unknown
一位中国科技YouTuber对Claude Sonnet 4.5和GPT-5 Codex进行了编程能力对比测试
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
UnverifiedB站UP主发布了一期对比测试，让Claude Sonnet 4.5与GPT-5 Codex用C++复刻1996年经典游戏《Terep 2》的软体物理驾驶模拟效果78% similarUnverifiedThe study tested AI coding performance across models including Sonnet 4.5, GPT 5.2, GPT 5.1 Mini, and Qwen 374% similarUnverified在SWE-bench软件工程任务基准测试上，Claude 3.5 Sonnet和GPT-4o的任务完成率远超开源模型72% similarVerifiedGPT-4、Claude 3.5 Sonnet、Gemini 1.5 Pro等新一代大语言模型在HumanEval、SWE-bench等代码能力基准测试上的得分已大幅超越此前版本72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/58009API
curl https://kongchang.com/api/v1/knowledge/claims/58009MCP
get_claim(id=58009)