The SuperCLUE November general large-model benchmark, released November 5, ranked Google's closed-source Gemini-4-Argon first with 73.62 points, followed by OpenAI's GPT-6.1-Sol at 71.76, among 19 domestic and foreign models tested across agent coding, math reasoning, long context, instruction following and hallucination control.
Moonshot AI's open-source Kimi-K3.1-Pro scored 61.46, the highest among open-source models and first among domestic models. DeepSeek-V4.1-Flash-1017 followed at 58.95 and Zhipu's GLM-5.3 at 50.66, forming the top tier of China's open-source models. Kimi-K3.1-Pro also led domestic models in hallucination control at 67.78.
Source: TechWeb / ZAKER
