DeepSeek-V3 is the stronger all-rounder.
Scores updated · 17 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.
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
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+39.8points ahead
Where Gemma (7B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results16 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.
- MultiPL-EDeepSeek-V3 by 53.483.129.7+53.4
- C-EvalDeepSeek-V3 by 42.986.543.6+42.9
- MMLU-ProDeepSeek-V3 by 42.275.933.7+42.2
- MATHDeepSeek-V3 by 40.290.250+40.2
- GSM8KDeepSeek-V3 by 38.19455.9+38.1
- ARC-ChallengeDeepSeek-V3 by 34.295.361.1+34.2
- BBHDeepSeek-V3 by 32.487.555.1+32.4
- MMLUDeepSeek-V3 by 31.488.557.1+31.4
- HumanEvalDeepSeek-V3 by 2865.237.2+28
- MBPPDeepSeek-V3 by 24.875.450.6+24.8
- OpenBookQADeepSeek-V3 by 14.695.480.8+14.6
- naturalquestions_closedbookDeepSeek-V3 by 13.146.733.6+13.1
- HellaSwagDeepSeek-V3 by 6.788.982.2+6.7
- PIQADeepSeek-V3 by 6.684.778.1+6.6
- WinoGrandeDeepSeek-V3 by 5.984.979+5.9
- NarrativeQADeepSeek-V3 by 4.479.675.2+4.4
Questions people ask
Which is better, DeepSeek-V3 or Gemma (7B)?
DeepSeek-V3 wins the one area where both have results: reasoning. Gemma (7B) wins none.
How do you compare the two?
We use the 17 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 16 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.