DeepSeek-R1-Zero is the stronger all-rounder.
Scores updated · 18 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 and reasoning 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-R1-Zero pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.8points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+1.2points ahead
Where DeepSeek-V3 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results16 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.
- AlpacaEval2.0 (LC-winrate)DeepSeek-V3 by 45.37024.7+45.3
- IFEvalDeepSeek-V3 by 39.586.146.6+39.5
- AIME 2024DeepSeek-R1-Zero by 38.739.277.9+38.7
- Aider-PolyglotDeepSeek-V3 by 37.449.612.2+37.4
- Arena-Hard (GPT-4-1106 judge)DeepSeek-V3 by 31.985.553.6+31.9
- CodeforcesDeepSeek-R1-Zero by 310 rating points11341444+310 rating
- FRAMES (Acc.)DeepSeek-R1-Zero by 973.382.3+9
- MMLU-ProDeepSeek-V3 by 775.968.9+7
- MATH-500 (EM)DeepSeek-R1-Zero by 5.790.295.9+5.7
- SimpleQADeepSeek-R1-Zero by 5.424.930.3+5.4
- MMLU-ReduxDeepSeek-V3 by 3.589.185.6+3.5
- DROP (3-shot F1)DeepSeek-V3 by 2.591.689.1+2.5
- CLUEWSCDeepSeek-R1-Zero by 2.290.993.1+2.2
- Chinese SimpleQA (C-SimpleQA)DeepSeek-V3 by 1.66866.4+1.6
- LiveCodeBenchtie49.250tie
- MMLUtie88.588.8tie
Questions people ask
Which is better, DeepSeek-V3 or DeepSeek-R1-Zero?
DeepSeek-R1-Zero wins all two areas where both have results: coding and reasoning. DeepSeek-V3 wins none.
Which is better for coding?
DeepSeek-R1-Zero. It wins the one coding test both models report.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.