待验证50% 置信事实精确时间
The five AI models tested were DeepSeek R1, Claude Sonnet 3.7, ChatGPT o3 Mini, Grok 3, and Qwen 2.5 Max.
1
来源数
50%
置信度
中期 (~90 天)
时效性
2026/7/2
首次发现
有效期至：2026/9/30
来源
Five AI Models Tested for Game Development: Which Is Best for Zero-Experience Coding?
bilibiliso-PHI-a_902025/3/1
相关事实
待验证The study tested AI coding performance across models including Sonnet 4.5, GPT 5.2, GPT 5.1 Mini, and Qwen 377% 相似待验证The four models tested in the AI coding comparison were ChatGPT 5.4, Gemini 3.1, DeepSeek V4 Pro, and Kimi 5.176% 相似待验证Trae支持Claude 3.7 Sonnet、Claude 3.5 Sonnet、GPT-4.0和DeepSeek R1满血版等AI模型73% 相似已验证DeepSeek V4在代码生成、数学推理等方面的表现与GPT-4o、Claude 3.5 Sonnet等顶级模型持平甚至超越72% 相似待验证本文测试了GPT-4o Mini、Qwen Max和本地Llama 3.1三个大模型在多Agent场景中的实际表现71% 相似
引用此条事实
Stable URI
https://kongchang.com/claim/60356API
curl https://kongchang.com/api/v1/knowledge/claims/60356MCP
get_claim(id=60356)