DeepSeek-V3 is the stronger all-rounder.
Scores updated · 16 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+29.2points ahead
Where Llama 3 (70B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results15 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 36.883.146.3+36.8
- ARC-ChallengeDeepSeek-V3 by 26.595.368.8+26.5
- MATHDeepSeek-V3 by 23.990.266.3+23.9
- MMLU-ProDeepSeek-V3 by 23.175.952.8+23.1
- CMMLUDeepSeek-V3 by 21.688.867.2+21.6
- C-EvalDeepSeek-V3 by 21.386.565.2+21.3
- MMLUDeepSeek-V3 by 1988.569.5+19
- HumanEvalDeepSeek-V3 by 1765.248.2+17
- GSM8KDeepSeek-V3 by 13.59480.5+13.5
- BBHDeepSeek-V3 by 6.587.581+6.5
- MBPPDeepSeek-V3 by 575.470.4+5
- OpenBookQADeepSeek-V3 by 295.493.4+2
- HellaSwagtie88.988tie
- naturalquestions_closedbooktie46.747.5tie
- NarrativeQAtie79.679.8tie
Questions people ask
Which is better, DeepSeek-V3 or Llama 3 (70B)?
DeepSeek-V3 wins the one area where both have results: reasoning. Llama 3 (70B) wins none.
How do you compare the two?
We use the 16 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 15 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.