DeepSeek-V3 is the stronger all-rounder.
Scores updated · 22 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
- Recent programming contest problemsLiveCodeBench v6+16.1points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+10.4points ahead
Where MiMo V2 Flash Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results20 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 19.290.271+19.2
- SuperGPQADeepSeek-V3 by 12.653.741.1+12.6
- HumanEvalMiMo V2 Flash Base by 12.265.277.4+12.2
- CRUXEval-O (output prediction)MiMo V2 Flash Base by 9.369.879.1+9.3
- MBPP+ (EvalPlus-augmented)DeepSeek-V3 by 7.478.871.4+7.4
- DROPDeepSeek-V3 by 6.991.684.7+6.9
- Chinese SimpleQA (C-SimpleQA)DeepSeek-V3 by 6.56861.5+6.5
- MBPPMiMo V2 Flash Base by 5.675.481+5.6
- SimpleQADeepSeek-V3 by 4.324.920.6+4.3
- MMLU-ProDeepSeek-V3 by 2.775.973.2+2.7
- MMLUDeepSeek-V3 by 1.888.586.7+1.8
- GSM8KDeepSeek-V3 by 1.79492.3+1.7
- MMLU-ReduxMiMo V2 Flash Base by 1.589.190.6+1.5
- C-EvalMiMo V2 Flash Base by 1.486.587.9+1.4
- CMMLUDeepSeek-V3 by 1.488.887.4+1.4
- WinoGrandeDeepSeek-V3 by 1.184.983.8+1.1
- BBHMiMo V2 Flash Base by 187.588.5+1
- ARC-Challengetie95.395.9tie
- HellaSwagtie88.988.5tie
- CRUXEval-I (input prediction)tie67.367.5tie
Questions people ask
Which is better, DeepSeek-V3 or MiMo V2 Flash Base?
DeepSeek-V3 wins all two areas where both have results: coding and reasoning. MiMo V2 Flash 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 22 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 20 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.