Unverified50% confidenceBenchmarkExact time
Since the second half of 2024, the performance of open-source models has closely approached that of closed-source models, with the ELO scores of Llama, DeepSeek, Zhipu GLM, and other open-source models nearing those of GPT-4o and Claude 3.5.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026
Sources
Related Claims
Unverified2024年下半年，Meta的Llama系列、DeepSeek、智谱GLM等开源模型的ELO积分已逼近GPT-4o和Claude 3.5的区间，分差压缩至个位数84% similarUnverified2023年末开源模型在 SWE-bench 上与 GPT-4 差距显著，闭源模型解决率约为开源模型的2-3倍81% similarUnverified以Qwen、DeepSeek、Llama为代表的开源/开放权重模型阵营正快速缩小与GPT-4o、Claude等顶级闭源模型的差距77% similarUnverifiedAt the end of 2023, there was a significant gap in programming capabilities between open-source models and GPT-4; by 2024–2025, domestic open-source models such as DeepSeek Coder, Qwen Coder, and the Kimi K series had substantially narrowed that gap.76% similarUnverified2024年初多个声称对标GPT-4的开源模型因训练数据疑似包含顶级闭源模型输出而引发质疑，OpenAI和Anthropic相继加强对异常访问模式的检测76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/590218API
curl https://kongchang.com/api/v1/knowledge/claims/590218MCP
get_claim(id=590218)