DeepSeek-R1-Distill-Qwen-32B vs Qwen2.5 Instruct 32B
Wins 2 of 2 areas
Coding · Reasoning
Wins 0 of 2 areas
—
DeepSeek-R1-Distill-Qwen-32B is the stronger all-rounder.
Scores updated · 7 tests both models report · How we compare
Where each one wins
Tests won in each of the two 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 rests on a single test.
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-R1-Distill-Qwen-32B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+14.9points ahead
- Code for real scientific research problemsSciCode+14.7points ahead
Where Qwen2.5 Instruct 32B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 7 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 14.737.622.9+14.7
ReasoningDeepSeek-R1-Distill-Qwen-32B
- GPQA DiamondDeepSeek-R1-Distill-Qwen-32B by 14.961.546.6+14.9
- Humanity's Last Examtie4.64tie
Other results4 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.
- KOR-BenchDeepSeek-R1-Distill-Qwen-32B by 11.966.654.7+11.9
- BBHDeepSeek-R1-Distill-Qwen-32B by 3.888.384.5+3.8
- BIG-Bench Extra HardDeepSeek-R1-Distill-Qwen-32B by 1.719.217.5+1.7
- AA IntelligenceDeepSeek-R1-Distill-Qwen-32B by 1.58.46.9+1.5
Questions people ask
Which is better, DeepSeek-R1-Distill-Qwen-32B or Qwen2.5 Instruct 32B?
DeepSeek-R1-Distill-Qwen-32B wins all two areas where both have results: coding and reasoning. Qwen2.5 Instruct 32B wins none.
Which is better for coding?
DeepSeek-R1-Distill-Qwen-32B. It wins the one coding test both models report.
How do you compare the two?
We use the 7 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 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.