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+9.6points ahead
Where Gemma (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 37.881.443.6+37.8
- ARC-ChallengeDeepSeek-V2 by 31.192.261.1+31.1
- BBHDeepSeek-V2 by 23.778.855.1+23.7
- GSM8KDeepSeek-V2 by 23.379.255.9+23.3
- Multi-MathematicsDeepSeek-V2 by 19.758.839.1+19.7
- MMLUDeepSeek-V2 by 18.575.657.1+18.5
- MMLU-ProDeepSeek-V2 by 17.751.433.7+17.7
- EvalPlusDeepSeek-V2 by 15.45539.6+15.4
- MultiPL-EDeepSeek-V2 by 14.744.429.7+14.7
- MBPPDeepSeek-V2 by 14.46550.6+14.4
- TriviaQADeepSeek-V2 by 7.679.972.3+7.6
- WinoGrandeDeepSeek-V2 by 7.386.379+7.3
- MATHGemma (7B) by 6.643.450+6.6
- HumanEvalDeepSeek-V2 by 6.143.337.2+6.1
- PIQADeepSeek-V2 by 5.883.978.1+5.8
- HellaSwagDeepSeek-V2 by 4.987.182.2+4.9
- TruthfulQAGemma (7B) by 2.642.244.8+2.6
Questions people ask
Which is better, DeepSeek-V2 or Gemma (7B)?
DeepSeek-V2 wins the one area where both have results: reasoning. Gemma (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.