MiMo V2 Flash 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 MiMo V2 Flash Base pulls ahead
- Recent programming contest problemsLiveCodeBench v6+1.5points ahead
Where DeepSeek-V3-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.
- MATHMiMo V2 Flash Base by 11.659.471+11.6
- MMLU-ProMiMo V2 Flash Base by 9.26473.2+9.2
- CRUXEval-O (output prediction)MiMo V2 Flash Base by 8.17179.1+8.1
- Chinese SimpleQA (C-SimpleQA)DeepSeek-V3-Base by 7.268.761.5+7.2
- IncludeDeepSeek-V3-Base by 6.577.971.4+6.5
- SimpleQADeepSeek-V3-Base by 5.626.120.6+5.6
- SuperGPQADeepSeek-V3-Base by 5.146.241.1+5.1
- GSM8KMiMo V2 Flash Base by 4.188.292.3+4.1
- MBPP+ (EvalPlus-augmented)DeepSeek-V3-Base by 4.175.571.4+4.1
- MMLU-ReduxMiMo V2 Flash Base by 3.886.890.6+3.8
- C-EvalDeepSeek-V3-Base by 2.590.387.9+2.5
- DROPDeepSeek-V3-Base by 1.886.584.7+1.8
- ARC-ChallengeMiMo V2 Flash Base by 1.294.795.9+1.2
- MMLUDeepSeek-V3-Base by 187.786.7+1
- CMMLUtie87.987.4tie
- CRUXEval-I (input prediction)tie67.867.5tie
Questions people ask
Which is better, DeepSeek-V3-Base or MiMo V2 Flash Base?
MiMo V2 Flash Base wins the one area where both have results: coding. DeepSeek-V3-Base wins none.
Which is better for coding?
MiMo V2 Flash 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.