Benchmark DeepSeek-R1 OpenAI o1-1217 AIME 2024 79.8% 79.2% Codeforces 96.3 percentile 89 percentile MATH-500 97.3% 96.4% SWE-bench Verified 49.2% 48.9% GPQA Diamond 71.5% 75.7% MMLU 90.8% 91.8% Key Takeaways: While both DeepSeek-R1 and OpenAI o1 exhibit impressive capabilities, they also have limitations: