OpenAI o3和DeepSeek R1在數學benchmarks的成績比較：

ChatGPT的回答：

Here's the comparison of math-related benchmark performance between OpenAI o3 and DeepSeek R1, excluding any benchmarks where one of the models’ numbers is unknown:

• AIME 2024:

  • OpenAI o3: 96.7% accuracy
  • DeepSeek R1: 79.8%

• Graduate-Level Google-Proof Q&A (GPQA) Benchmark:

  • OpenAI o3: 87.7%
  • DeepSeek R1: 71.5%

The MATH-500 benchmark data is only available for DeepSeek R1, so no comparison is made for that benchmark.

 

所有跟帖： 

• 謝謝double check。我用的是free o3。你再試一下，2023 AIME I p15 -bigcat2026- ♂ (0 bytes) () 02/01/2025 postreply 22:53:43

• 謝謝！借這貼問一下，chatGPT, Deepseek, Gemini, Copolit 這些tools -newca- ♀ (400 bytes) () 02/02/2025 postreply 03:55:49