DeepSeek-V3 vs QwQ 32B Preview
Wins 3 of 4 areas
Coding · Long documents · Following instructions
Wins 0 of 4 areas
—
DeepSeek-V3 is the stronger all-rounder.
Scores updated · 19 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.
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-V3 costs 31% 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
- Reasons across sets of long documentsAA-LCR+14points ahead
- Recent programming contest problemsLiveCodeBench v6+7.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.2points ahead
Where QwQ 32B Preview pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+2.7points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- LiveCodeBench v6DeepSeek-V3 by 7.846.939.1+7.8
- SciCodeDeepSeek-V3 by 3.23935.8+3.2
ReasoningEven
- GPQA DiamondDeepSeek-V3 by 6.265.559.3+6.2
- Humanity's Last ExamQwQ 32B Preview by 2.74.77.3+2.7
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 2.24138.8+2.2
Other results13 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.
- Aider-PolyglotDeepSeek-V3 by 28.749.620.9+28.7
- MMLU-ProDeepSeek-V3 by 23.975.952+23.9
- DROP (3-shot F1)DeepSeek-V3 by 20.491.671.2+20.4
- Codeforces (Rating)QwQ 32B Preview by 182 rating points11341316+182 rating
- AIME 2025DeepSeek-V3 by 1851.333.3+18
- HMMT Feb. 2025DeepSeek-V3 by 10.929.218.3+10.9
- AIME 2024QwQ 32B Preview by 10.839.250+10.8
- SuperGPQADeepSeek-V3 by 10.153.743.6+10.1
- IFEvalDeepSeek-V3 by 2.286.183.9+2.2
- LiveCodeBenchtie49.250tie
- LiveBenchtie72.473.1tie
- MATH-500 (EM)tie90.290.6tie
- AA Intelligencetie9.79.5tie
Questions people ask
Which is better, DeepSeek-V3 or QwQ 32B Preview?
DeepSeek-V3 wins three of the four areas where both have results: coding, long documents and following instructions. QwQ 32B Preview wins none. They are level on reasoning.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; QwQ 32B Preview wins none.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; QwQ 32B Preview costs $0.66 and $1.00. That makes DeepSeek-V3 about 31% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.