DeepSeek-V2 is the stronger all-rounder.
Scores updated · 18 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 DeepSeek-V2 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+10.6points ahead
Where Mistral 7B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results17 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.
- C-EvalDeepSeek-V2 by 3481.447.4+34
- Multi-MathematicsDeepSeek-V2 by 32.558.826.3+32.5
- ARC-ChallengeDeepSeek-V2 by 32.292.260+32.2
- MATHDeepSeek-V2 by 30.343.413.1+30.3
- GSM8KDeepSeek-V2 by 2779.252.2+27
- BBHDeepSeek-V2 by 22.778.856.1+22.7
- MMLU-ProDeepSeek-V2 by 20.551.430.9+20.5
- EvalPlusDeepSeek-V2 by 18.65536.4+18.6
- MultiPL-EDeepSeek-V2 by 1544.429.4+15
- HumanEvalDeepSeek-V2 by 1443.329.3+14
- MBPPDeepSeek-V2 by 13.96551.1+13.9
- MMLUDeepSeek-V2 by 11.475.664.2+11.4
- WinoGrandeDeepSeek-V2 by 7.986.378.4+7.9
- PIQADeepSeek-V2 by 6.283.977.7+6.2
- TriviaQADeepSeek-V2 by 4.779.975.2+4.7
- HellaSwagDeepSeek-V2 by 3.987.183.2+3.9
- TruthfulQAtie42.242.2tie
Questions people ask
Which is better, DeepSeek-V2 or Mistral 7B?
DeepSeek-V2 wins the one area where both have results: reasoning. Mistral 7B wins none.
How do you compare the two?
We use the 18 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 17 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.