DeepSeek V3.2 has released its latest results in the Livebench benchmark, providing a comprehensive comparison with leading AI models in the industry such as Claude 4.5 Opus Thinking, Gemini 3 Pro Preview, and GPT-5. The test results show that V3.2 ranked ninth in reasoning tasks, sixteenth in programming ability, fourteenth in agent programming capability, tenth in mathematical ability, and demonstrated outstanding performance in data analysis, ranking third. These data points reflect the rapid iteration of current AI technology and intense competition among models, offering valuable reference for AI professionals, researchers, and developers to evaluate the performance advantages of different models and drive the advancement of artificial intelligence technology. The test results also highlight DeepSeek’s competitiveness in specific domains, particularly its strong performance in data analysis.
