Mistral Medium (Non-Reasoning) wins more areas, narrowly.
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 Mistral Medium (Non-Reasoning) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.5points ahead
- Code for real scientific research problemsSciCode+5.5points ahead
Where Command R pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.3points ahead
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.
CodingMistral Medium (Non-Reasoning)
- SciCodeMistral Medium (Non-Reasoning) by 5.56.311.8+5.5
ReasoningEven
- GPQA DiamondMistral Medium (Non-Reasoning) by 6.528.434.9+6.5
- Humanity's Last ExamCommand R by 1.34.83.5+1.3
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.
- MATHMistral Medium (Non-Reasoning) by 3026.656.5+30
- NarrativeQACommand R by 29.374.244.9+29.3
- GSM8KMistral Medium (Non-Reasoning) by 15.555.170.6+15.5
- naturalquestions_closedbookCommand R by 6.235.229+6.2
- MMLUMistral Medium (Non-Reasoning) by 5.156.761.8+5.1
- OpenBookQAMistral Medium (Non-Reasoning) by 4.878.283+4.8
- AA Intelligencetie55.5tie
Questions people ask
Which is better, Command R or Mistral Medium (Non-Reasoning)?
Mistral Medium (Non-Reasoning) wins one of the two areas where both have results: coding. Command R wins none. They are level on reasoning.
Which is better for coding?
Mistral Medium (Non-Reasoning). 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.