DeepSeek-V3 is the stronger all-rounder.Qwen 2.5 Coder 32B Instruct is cheaper.
Scores updated · 14 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.
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.
Qwen 2.5 Coder 32B Instruct costs 77% 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 DeepSeek-V3 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+33points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+23.8points ahead
- Code for real scientific research problemsSciCode+11.9points ahead
Where Qwen 2.5 Coder 32B Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- SWE-bench VerifiedDeepSeek-V3 by 33429+33
- SciCodeDeepSeek-V3 by 11.93927.1+11.9
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 23.865.541.7+23.8
- Humanity's Last ExamDeepSeek-V3 by 1.24.73.5+1.2
Other results10 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.
- HumanEvalQwen 2.5 Coder 32B Instruct by 27.565.292.7+27.5
- MMLU-ProDeepSeek-V3 by 25.575.950.4+25.5
- ARC-ChallengeDeepSeek-V3 by 24.895.370.5+24.8
- LiveCodeBenchDeepSeek-V3 by 17.849.231.4+17.8
- MBPPQwen 2.5 Coder 32B Instruct by 14.875.490.2+14.8
- MMLU-ReduxDeepSeek-V3 by 11.689.177.5+11.6
- HellaSwagDeepSeek-V3 by 5.988.983+5.9
- WinoGrandeDeepSeek-V3 by 4.184.980.8+4.1
- AA IntelligenceDeepSeek-V3 by 39.76.7+3
- GSM8KDeepSeek-V3 by 2.99491.1+2.9
Questions people ask
Which is better, DeepSeek-V3 or Qwen 2.5 Coder 32B Instruct?
DeepSeek-V3 wins all two areas where both have results: coding and reasoning. Qwen 2.5 Coder 32B Instruct wins none, but costs 77% less.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Qwen 2.5 Coder 32B Instruct wins none.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Qwen 2.5 Coder 32B Instruct costs $0.06 and $0.20. That makes Qwen 2.5 Coder 32B Instruct about 77% cheaper for the same work.
How do you compare the two?
We use the 14 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.