DeepSeek-V3 is the stronger all-rounder.
Scores updated · 16 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.
Reasoning rests on a single test.
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
- Recent programming contest problemsLiveCodeBench v6+11.4points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+11.2points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.4points ahead
Where MiMo V2.5 Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- LiveCodeBench v6DeepSeek-V3 by 11.446.935.5+11.4
- SWE-bench VerifiedDeepSeek-V3 by 11.24230.8+11.2
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.
- MATHDeepSeek-V3 by 22.590.267.7+22.5
- GSM8KDeepSeek-V3 by 10.79483.3+10.7
- MMLU-ProDeepSeek-V3 by 10.175.965.8+10.1
- DROPDeepSeek-V3 by 7.991.683.7+7.9
- MBPP+ (EvalPlus-augmented)DeepSeek-V3 by 7.978.870.9+7.9
- MMLUDeepSeek-V3 by 2.288.586.3+2.2
- C-EvalMiMo V2.5 Base by 2.186.588.6+2.1
- ARC-ChallengeMiMo V2.5 Base by 1.295.396.5+1.2
- MMLU-Reduxtie89.189.8tie
- CMMLUtie88.888.2tie
- BBHtie87.587.2tie
- HellaSwagtie88.988.6tie
- WinoGrandetie84.984.7tie
Questions people ask
Which is better, DeepSeek-V3 or MiMo V2.5 Base?
DeepSeek-V3 wins all two areas where both have results: coding and reasoning. MiMo V2.5 Base wins none.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; MiMo V2.5 Base wins none.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 3 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.