The two are evenly matched.DeepSeek-V3 is better at coding; MiMo V2.5 Pro Base at reasoning.
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+7.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+6.3points ahead
Where MiMo V2.5 Pro Base pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1.2points ahead
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 7.346.939.6+7.3
- SWE-bench VerifiedDeepSeek-V3 by 6.34235.7+6.3
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.
- MMLU-ProDeepSeek-V3 by 7.475.968.5+7.4
- GSM8KMiMo V2.5 Pro Base by 5.69499.6+5.6
- DROPDeepSeek-V3 by 5.391.686.3+5.3
- C-EvalMiMo V2.5 Pro Base by 586.591.5+5
- MBPP+ (EvalPlus-augmented)DeepSeek-V3 by 4.778.874.1+4.7
- MATHDeepSeek-V3 by 490.286.2+4
- MMLU-ReduxMiMo V2.5 Pro Base by 3.789.192.8+3.7
- ARC-ChallengeMiMo V2.5 Pro Base by 1.995.397.2+1.9
- CMMLUMiMo V2.5 Pro Base by 1.488.890.2+1.4
- BBHtie87.588.4tie
- HellaSwagtie88.989.8tie
- MMLUtie88.589.4tie
- WinoGrandetie84.985.6tie
Questions people ask
Which is better, DeepSeek-V3 or MiMo V2.5 Pro Base?
DeepSeek-V3 and MiMo V2.5 Pro Base each win one of the two areas where both have results. DeepSeek-V3 wins coding; MiMo V2.5 Pro Base wins reasoning.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; MiMo V2.5 Pro 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.