DeepSeek R1 vs o1
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
o1 by OpenAI wins on 10 of 18 benchmarks against DeepSeek R1 by DeepSeek, which leads on 7. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from our benchmark data.
Category-by-Category Breakdown
General Intelligence: In general intelligence, o1 scores 1360 on Chatbot Arena ELO compared to DeepSeek R1's 1355, while DeepSeek R1 scores 84.0% on MMLU-Pro compared to o1's 82.0%, while o1 scores 92.0% on IFEval compared to DeepSeek R1's 87.8%, while o1 scores 47.0% on SimpleQA compared to DeepSeek R1's 30.1%.
Coding: In coding, o1 scores 89.0% on HumanEval+ compared to DeepSeek R1's 86.0%, while DeepSeek R1 scores 49.2% on SWE-bench Verified compared to o1's 48.9%, while o1 scores 55.0% on LiveCodeBench compared to DeepSeek R1's 50.0%, while o1 scores 39.7 on AA Coding Index compared to DeepSeek R1's 24.6.
Math: In math, DeepSeek R1 scores 97.3% on MATH compared to o1's 94.8%, while o1 scores 97.5% on GSM8K compared to DeepSeek R1's 97.0%, while DeepSeek R1 scores 79.8% on AIME 2025 compared to o1's 74.0%.
Reasoning: In reasoning, o1 scores 77.3% on GPQA Diamond compared to DeepSeek R1's 71.5%, while o1 scores 32.0% on ARC-AGI compared to DeepSeek R1's 14.0%.
Context: In context, o1 scores 200K on Context Length compared to DeepSeek R1's 64K.
Pricing Comparison
DeepSeek R1 costs $0.70/1M input tokens and $2.5/1M output tokens, while o1 costs $15.0/1M input and $60.0/1M output. DeepSeek R1 is the more affordable option for API usage.
Speed Comparison
DeepSeek R1 generates output at 35 tok/s compared to o1's 35 tok/s, and the time to first token is 950 ms for DeepSeek R1 versus 1000 ms for o1. Both models offer similar output speed.
Verdict
For developers prioritizing coding and math and affordability, DeepSeek R1 has the edge. For those who value general intelligence, o1 is the stronger choice.
View Individual Model Pages
DeepSeek R1 vs o1 — FAQ
Which is better, DeepSeek R1 or o1?
o1 wins on more benchmarks overall (10 vs 7). However, the best choice depends on your specific needs — each model excels in different areas.
How does DeepSeek R1 compare to o1 for coding?
DeepSeek R1 is better for coding, scoring 49.2% on SWE-bench Verified compared to 48.9%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is DeepSeek R1 cheaper than o1?
Yes, DeepSeek R1 is cheaper. DeepSeek R1 costs $0.70/1M input and $2.5/1M output tokens. o1 costs $15.0/1M input and $60.0/1M output tokens.
Which is faster, DeepSeek R1 or o1?
Both models generate output at the same speed of 35 tok/s.
What benchmarks does the DeepSeek R1 vs o1 comparison cover?
This comparison covers 18 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, IFEval, SimpleQA, MATH, GPQA Diamond, SWE-bench Verified, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.