DeepSeek R1 0528 vs Qwen 2.5 72B
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
DeepSeek R1 0528 by DeepSeek wins on 9 of 14 benchmarks against Qwen 2.5 72B by Qwen, which leads on 4. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from the AI Value Index.
Category-by-Category Breakdown
General Intelligence: In general intelligence, DeepSeek R1 0528 scores 1375 on Chatbot Arena ELO compared to Qwen 2.5 72B's 1230, while DeepSeek R1 0528 scores 84.0% on MMLU-Pro compared to Qwen 2.5 72B's 72.0%.
Coding: In coding, DeepSeek R1 0528 scores 88.0% on HumanEval+ compared to Qwen 2.5 72B's 80.0%, while DeepSeek R1 0528 scores 55.0% on SWE-bench Verified compared to Qwen 2.5 72B's 28.0%, while DeepSeek R1 0528 scores 58.0% on LiveCodeBench compared to Qwen 2.5 72B's 55.5%.
Math: In math, DeepSeek R1 0528 scores 96.0% on MATH compared to Qwen 2.5 72B's 83.1%, while DeepSeek R1 0528 scores 97.5% on GSM8K compared to Qwen 2.5 72B's 91.0%.
Reasoning: In reasoning, DeepSeek R1 0528 scores 81.0% on GPQA Diamond compared to Qwen 2.5 72B's 49.1%, while DeepSeek R1 0528 scores 15.0% on ARC-AGI compared to Qwen 2.5 72B's 12.0%.
Context: In context, both score 131K on Context Length.
Pricing Comparison
DeepSeek R1 0528 costs $0.55/1M input tokens and $2.2/1M output tokens, while Qwen 2.5 72B costs $0.12/1M input and $0.39/1M output. Qwen 2.5 72B is the more affordable option for API usage.
Speed Comparison
DeepSeek R1 0528 generates output at 40 tok/s compared to Qwen 2.5 72B's 80 tok/s, and the time to first token is 900 ms for DeepSeek R1 0528 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, DeepSeek R1 0528 has the edge. For those who value affordability and speed, Qwen 2.5 72B is the stronger choice.
View Individual Model Pages
DeepSeek R1 0528 vs Qwen 2.5 72B — FAQ
Which is better, DeepSeek R1 0528 or Qwen 2.5 72B?
DeepSeek R1 0528 wins on more benchmarks overall (9 vs 4). However, the best choice depends on your specific needs — each model excels in different areas.
How does DeepSeek R1 0528 compare to Qwen 2.5 72B for coding?
DeepSeek R1 0528 is better for coding, scoring 55.0% on SWE-bench Verified compared to 28.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is DeepSeek R1 0528 cheaper than Qwen 2.5 72B?
Yes, Qwen 2.5 72B is cheaper. DeepSeek R1 0528 costs $0.55/1M input and $2.2/1M output tokens. Qwen 2.5 72B costs $0.12/1M input and $0.39/1M output tokens.
Which is faster, DeepSeek R1 0528 or Qwen 2.5 72B?
Qwen 2.5 72B is faster, generating output at 80 tok/s compared to 40 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the DeepSeek R1 0528 vs Qwen 2.5 72B comparison cover?
This comparison covers 14 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MATH, SWE-bench Verified, GPQA Diamond, Output Speed, Time to First Token, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.