MiMo V2.5 Base is the stronger all-rounder.
Scores updated · 20 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where MiMo V2.5 Base pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+26.3points ahead
- Recent programming contest problemsLiveCodeBench v6+10.6points ahead
Where DeepSeek-V3.2-Exp-Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results18 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.
- aime_2024_2025_combinedMiMo V2.5 Base by 12.124.836.9+12.1
- MATHMiMo V2.5 Base by 7.660.167.7+7.6
- GlobalMMLUDeepSeek-V3.2-Exp-Base by 4.68277.4+4.6
- HumanEval+MiMo V2.5 Base by 3.667.771.3+3.6
- TriviaQADeepSeek-V3.2-Exp-Base by 3.283.980.7+3.2
- DROPDeepSeek-V3.2-Exp-Base by 2.986.683.7+2.9
- MMLU-ProMiMo V2.5 Base by 2.563.365.8+2.5
- C-EvalDeepSeek-V3.2-Exp-Base by 2.49188.6+2.4
- BBHDeepSeek-V3.2-Exp-Base by 1.588.787.2+1.5
- MMLUDeepSeek-V3.2-Exp-Base by 1.587.886.3+1.5
- ARC-ChallengeMiMo V2.5 Base by 1.395.296.5+1.3
- WinoGrandeMiMo V2.5 Base by 1.383.484.7+1.3
- GSM8KDeepSeek-V3.2-Exp-Base by 1.184.483.3+1.1
- MBPP+MiMo V2.5 Base by 1.169.870.9+1.1
- MBPP+ (EvalPlus-augmented)MiMo V2.5 Base by 1.169.870.9+1.1
- HellaSwagtie89.488.6tie
- CMMLUtie88.988.2tie
- MMLU-Reduxtie90.489.8tie
Questions people ask
Which is better, DeepSeek-V3.2-Exp-Base or MiMo V2.5 Base?
MiMo V2.5 Base wins all two areas where both have results: coding and reasoning. DeepSeek-V3.2-Exp-Base wins none.
Which is better for coding?
MiMo V2.5 Base. It wins the one coding test both models report.
How do you compare the two?
We use the 20 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 18 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.