DeepSeek R1 0528 vs Qwen 3.5 397B
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
DeepSeek R1 0528 by DeepSeek wins on 8 of 14 benchmarks against Qwen 3.5 397B 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 3.5 397B's 1350, while DeepSeek R1 0528 scores 84.0% on MMLU-Pro compared to Qwen 3.5 397B's 81.0%.
Coding: In coding, both score 88.0% on HumanEval+, while Qwen 3.5 397B scores 76.4% on SWE-bench Verified compared to DeepSeek R1 0528's 55.0%, while DeepSeek R1 0528 scores 58.0% on LiveCodeBench compared to Qwen 3.5 397B's 54.0%.
Math: In math, DeepSeek R1 0528 scores 96.0% on MATH compared to Qwen 3.5 397B's 87.0%, while DeepSeek R1 0528 scores 97.5% on GSM8K compared to Qwen 3.5 397B's 95.0%.
Reasoning: In reasoning, DeepSeek R1 0528 scores 81.0% on GPQA Diamond compared to Qwen 3.5 397B's 62.0%, while Qwen 3.5 397B scores 45.0% on ARC-AGI compared to DeepSeek R1 0528's 15.0%.
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 3.5 397B costs $0.60/1M input and $3.6/1M output. DeepSeek R1 0528 is the more affordable option for API usage.
Speed Comparison
DeepSeek R1 0528 generates output at 40 tok/s compared to Qwen 3.5 397B's 45 tok/s, and the time to first token is 900 ms for DeepSeek R1 0528 versus 600 ms for Qwen 3.5 397B. Qwen 3.5 397B delivers faster throughput.
Verdict
For developers prioritizing general intelligence and math and affordability, DeepSeek R1 0528 has the edge. For those who value coding and speed, Qwen 3.5 397B is the stronger choice.
View Individual Model Pages
DeepSeek R1 0528 vs Qwen 3.5 397B — FAQ
Which is better, DeepSeek R1 0528 or Qwen 3.5 397B?
DeepSeek R1 0528 wins on more benchmarks overall (8 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 3.5 397B for coding?
Qwen 3.5 397B is better for coding, scoring 76.4% on SWE-bench Verified compared to 55.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is DeepSeek R1 0528 cheaper than Qwen 3.5 397B?
Yes, DeepSeek R1 0528 is cheaper. DeepSeek R1 0528 costs $0.55/1M input and $2.2/1M output tokens. Qwen 3.5 397B costs $0.60/1M input and $3.6/1M output tokens.
Which is faster, DeepSeek R1 0528 or Qwen 3.5 397B?
Qwen 3.5 397B is faster, generating output at 45 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 3.5 397B 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.