DeepSeek-V3 is the stronger all-rounder.
Scores updated · 25 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-V3 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+33.7points ahead
- Recent programming contest problemsLiveCodeBench v6+22points ahead
Where DeepSeek-V3.2-Exp-Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results23 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.
- OpenBookQADeepSeek-V3 by 47.295.448.2+47.2
- MATHDeepSeek-V3 by 30.190.260.1+30.1
- MMLU-ProDeepSeek-V3 by 12.675.963.3+12.6
- SuperGPQADeepSeek-V3 by 10.153.743.6+10.1
- GSM8KDeepSeek-V3 by 9.69484.4+9.6
- MBPP+ (EvalPlus-augmented)DeepSeek-V3 by 978.869.8+9
- CRUXEval-O (output prediction)DeepSeek-V3.2-Exp-Base by 5.169.874.9+5.1
- DROPDeepSeek-V3 by 591.686.6+5
- C-EvalDeepSeek-V3.2-Exp-Base by 4.586.591+4.5
- CRUXEval-I (input prediction)DeepSeek-V3 by 3.467.363.9+3.4
- HumanEvalDeepSeek-V3 by 3.365.261.9+3.3
- MGSMDeepSeek-V3.2-Exp-Base by 2.579.882.3+2.5
- SimpleQADeepSeek-V3.2-Exp-Base by 2.124.927+2.1
- WinoGrandeDeepSeek-V3 by 1.584.983.4+1.5
- MMLU-ReduxDeepSeek-V3.2-Exp-Base by 1.389.190.4+1.3
- BBHDeepSeek-V3.2-Exp-Base by 1.287.588.7+1.2
- MMLUtie88.587.8tie
- HellaSwagtie88.989.4tie
- PIQAtie84.785.1tie
- MBPPtie75.475.6tie
- ARC-Challengetie95.395.2tie
- CMMLUtie88.888.9tie
- Chinese SimpleQA (C-SimpleQA)tie6868tie
Questions people ask
Which is better, DeepSeek-V3 or DeepSeek-V3.2-Exp-Base?
DeepSeek-V3 wins all two areas where both have results: coding and reasoning. DeepSeek-V3.2-Exp-Base wins none.
Which is better for coding?
DeepSeek-V3. It wins the one coding test both models report.
How do you compare the two?
We use the 25 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 23 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.