DeepSeek-R1-Distill-Qwen-32B vs QwQ 32B Preview
Wins 1 of 4 areas
Coding
Wins 2 of 4 areas
Long documents · Following instructions
QwQ 32B Preview wins more areas, narrowly.DeepSeek-R1-Distill-Qwen-32B is cheaper and better at coding.
Scores updated · 12 tests both models report · How we compare
Where each one wins
Tests won in each of the four areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding, long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
DeepSeek-R1-Distill-Qwen-32B costs 65% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where QwQ 32B Preview pulls ahead
- Reasons across sets of long documentsAA-LCR+18points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.9points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+2.8points ahead
Where DeepSeek-R1-Distill-Qwen-32B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.2points ahead
- Code for real scientific research problemsSciCode+1.8points ahead
Every test, side by side
All 12 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-R1-Distill-Qwen-32B
- SciCodeDeepSeek-R1-Distill-Qwen-32B by 1.837.635.8+1.8
ReasoningEven
- Humanity's Last ExamQwQ 32B Preview by 2.84.67.3+2.8
- GPQA DiamondDeepSeek-R1-Distill-Qwen-32B by 2.261.559.3+2.2
Following instructionsQwQ 32B Preview
- IFBenchQwQ 32B Preview by 15.922.938.8+15.9
Other results7 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- Codeforces (Rating)DeepSeek-R1-Distill-Qwen-32B by 375 rating points16911316+375 rating
- AIME 2025DeepSeek-R1-Distill-Qwen-32B by 26.76033.3+26.7
- AIME 2024DeepSeek-R1-Distill-Qwen-32B by 22.672.650+22.6
- HMMT Feb. 2025DeepSeek-R1-Distill-Qwen-32B by 1533.318.3+15
- LiveCodeBenchDeepSeek-R1-Distill-Qwen-32B by 7.257.250+7.2
- MATH-500 (EM)DeepSeek-R1-Distill-Qwen-32B by 3.794.390.6+3.7
- AA IntelligenceQwQ 32B Preview by 1.18.49.5+1.1
Questions people ask
Which is better, DeepSeek-R1-Distill-Qwen-32B or QwQ 32B Preview?
QwQ 32B Preview wins two of the four areas where both have results: long documents and following instructions. DeepSeek-R1-Distill-Qwen-32B wins coding, and costs 65% less. They are level on reasoning.
Which is better for coding?
DeepSeek-R1-Distill-Qwen-32B. It wins the one coding test both models report.
Which is cheaper?
DeepSeek-R1-Distill-Qwen-32B costs $0.29 per million input tokens and $0.29 per million output tokens; QwQ 32B Preview costs $0.66 and $1.00. That makes DeepSeek-R1-Distill-Qwen-32B about 65% cheaper for the same work.
How do you compare the two?
We use the 12 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.