DeepSeek-V3-Base is the stronger all-rounder.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the one area 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-V3-Base pulls ahead
- Recent programming contest problemsLiveCodeBench v6+4.5points ahead
Where DeepSeek-V3.1-Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 17 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.
- CRUXEval-I (input prediction)DeepSeek-V3-Base by 5.762.167.8+5.7
- CRUXEval-O (output prediction)DeepSeek-V3.1-Base by 5.476.471+5.4
- MMLU-ProDeepSeek-V3-Base by 5.258.864+5.2
- SuperGPQADeepSeek-V3-Base by 3.942.346.2+3.9
- MBPP+ (EvalPlus-augmented)DeepSeek-V3-Base by 3.372.275.5+3.3
- GSM8KDeepSeek-V3.1-Base by 3.291.488.2+3.2
- MATHDeepSeek-V3.1-Base by 3.262.659.4+3.2
- MMLU-ReduxDeepSeek-V3.1-Base by 3.29086.8+3.2
- Chinese SimpleQA (C-SimpleQA)DeepSeek-V3.1-Base by 2.270.968.7+2.2
- ARC-Challengetie95.694.7tie
- CMMLUtie88.887.9tie
- Includetie77.277.9tie
- C-Evaltie9090.3tie
- MMLUtie87.487.7tie
- DROPtie86.386.5tie
- SimpleQAtie26.326.1tie
Questions people ask
Which is better, DeepSeek-V3.1-Base or DeepSeek-V3-Base?
DeepSeek-V3-Base wins the one area where both have results: coding. DeepSeek-V3.1-Base wins none.
Which is better for coding?
DeepSeek-V3-Base. It wins the one coding test both models report.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 1 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.