Mistral Large 3 675B Base 2512 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 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.
Reasoning 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 Mistral Large 3 675B Base 2512 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+12.1points 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.
ReasoningMistral Large 3 675B Base 2512
- GPQA DiamondMistral Large 3 675B Base 2512 by 12.131.843.9+12.1
Other results19 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.
- RULER 128KDeepSeek-V3.2-Exp-Base by 36.191.955.8+36.1
- MBPP-SanitizedMistral Large 3 675B Base 2512 by 25.458.784.1+25.4
- GSM8KMistral Large 3 675B Base 2512 by 6.884.491.2+6.8
- HumanEvalMistral Large 3 675B Base 2512 by 4.861.966.7+4.8
- MMLU-ProMistral Large 3 675B Base 2512 by 4.163.367.4+4.1
- OpenBookQAMistral Large 3 675B Base 2512 by 3.248.251.4+3.2
- RULER 64KDeepSeek-V3.2-Exp-Base by 3.293.390.1+3.2
- SimpleQADeepSeek-V3.2-Exp-Base by 3.22723.8+3.2
- MATHMistral Large 3 675B Base 2512 by 2.860.162.9+2.8
- GPQA (unspecified)DeepSeek-V3.2-Exp-Base by 2.437.334.9+2.4
- ARC-ChallengeMistral Large 3 675B Base 2512 by 2.195.297.3+2.1
- Global-MMLU-LiteMistral Large 3 675B Base 2512 by 1.785.687.3+1.7
- WinoGrandeDeepSeek-V3.2-Exp-Base by 1.383.482.1+1.3
- AGIEval-Entie70.169.3tie
- MGSMtie82.382.9tie
- HellaSwagtie89.488.9tie
- MMLUtie87.887.3tie
- PIQAtie85.184.8tie
- RACEtie93.293.3tie
Questions people ask
Which is better, DeepSeek-V3.2-Exp-Base or Mistral Large 3 675B Base 2512?
Mistral Large 3 675B Base 2512 wins the one area where both have results: reasoning. DeepSeek-V3.2-Exp-Base wins none.
How do you compare the two?
We use the 20 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 19 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.