Claude 3 Sonnet is the stronger all-rounder.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas 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.
Coding 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 Claude 3 Sonnet pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+4.9points ahead
- Code for real scientific research problemsSciCode+2.1points ahead
Where Mistral Large pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningClaude 3 Sonnet
- GPQA DiamondClaude 3 Sonnet by 4.94035.1+4.9
- Humanity's Last Examtie3.63.5tie
Other results7 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.
- NarrativeQAMistral Large by 34.311.145.4+34.3
- MATHMistral Large by 31.943.175+31.9
- naturalquestions_closedbookMistral Large by 28.32.831.1+28.3
- GSM8KClaude 3 Sonnet by 22.992.369.4+22.9
- MMLUClaude 3 Sonnet by 14.578.363.8+14.5
- OpenBookQAClaude 3 Sonnet by 2.491.889.4+2.4
- AA Intelligencetie5.95.8tie
Questions people ask
Which is better, Claude 3 Sonnet or Mistral Large?
Claude 3 Sonnet wins all two areas where both have results: coding and reasoning. Mistral Large wins none.
Which is better for coding?
Claude 3 Sonnet. It wins the one coding test both models report.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.