o1 vs Qwen 2.5 72B
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
o1 by OpenAI wins on 9 of 14 benchmarks against Qwen 2.5 72B by Qwen, which leads on 5. 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 Qwen 2.5 72B's 1230, while o1 scores 82.0% on MMLU-Pro compared to Qwen 2.5 72B's 72.0%.
Coding: In coding, o1 scores 89.0% on HumanEval+ compared to Qwen 2.5 72B's 80.0%, while o1 scores 48.9% on SWE-bench Verified compared to Qwen 2.5 72B's 28.0%, while Qwen 2.5 72B scores 55.5% on LiveCodeBench compared to o1's 55.0%.
Math: In math, o1 scores 94.8% on MATH compared to Qwen 2.5 72B's 83.1%, while o1 scores 97.5% on GSM8K compared to Qwen 2.5 72B's 91.0%.
Reasoning: In reasoning, o1 scores 77.3% on GPQA Diamond compared to Qwen 2.5 72B's 49.1%, while o1 scores 32.0% on ARC-AGI compared to Qwen 2.5 72B's 12.0%.
Context: In context, o1 scores 200K on Context Length compared to Qwen 2.5 72B's 33K.
Pricing Comparison
o1 costs $15.0/1M input tokens and $60.0/1M output tokens, while Qwen 2.5 72B costs $0.36/1M input and $0.40/1M output. Qwen 2.5 72B is the more affordable option for API usage.
Speed Comparison
o1 generates output at 35 tok/s compared to Qwen 2.5 72B's 80 tok/s, and the time to first token is 1000 ms for o1 versus 350 ms for Qwen 2.5 72B. Qwen 2.5 72B delivers faster throughput.
Verdict
For developers prioritizing coding and general intelligence and math, o1 has the edge. For those who value affordability and speed, Qwen 2.5 72B is the stronger choice.
View Individual Model Pages
o1 vs Qwen 2.5 72B — FAQ
Which is better, o1 or Qwen 2.5 72B?
o1 wins on more benchmarks overall (9 vs 5). However, the best choice depends on your specific needs — each model excels in different areas.
How does o1 compare to Qwen 2.5 72B for coding?
o1 is better for coding, scoring 48.9% on SWE-bench Verified compared to 28.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is o1 cheaper than Qwen 2.5 72B?
Yes, Qwen 2.5 72B is cheaper. o1 costs $15.0/1M input and $60.0/1M output tokens. Qwen 2.5 72B costs $0.36/1M input and $0.40/1M output tokens.
Which is faster, o1 or Qwen 2.5 72B?
Qwen 2.5 72B is faster, generating output at 80 tok/s compared to 35 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the o1 vs Qwen 2.5 72B comparison cover?
This comparison covers 14 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MATH, GPQA Diamond, SWE-bench Verified, Output Speed, LiveCodeBench, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.