The two are evenly matched.Command R+ (Apr '24) is better at reasoning; Mistral Small (2402) at coding.
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 Command R+ (Apr '24) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.1points ahead
Where Mistral Small (2402) pulls ahead
- Code for real scientific research problemsSciCode+1.6points 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.
ReasoningCommand R+ (Apr '24)
- GPQA DiamondCommand R+ (Apr '24) by 2.132.330.2+2.1
- Humanity's Last Examtie4.64.1tie
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 Small (2402) by 21.840.362+21.8
- NarrativeQACommand R+ (Apr '24) by 21.673.551.9+21.6
- naturalquestions_closedbookCommand R+ (Apr '24) by 3.934.330.4+3.9
- OpenBookQAMistral Small (2402) by 3.482.886.2+3.4
- GSM8KMistral Small (2402) by 2.770.773.4+2.7
- MMLUtie5959.3tie
- AA Intelligencetie5.35.5tie
Questions people ask
Which is better, Command R+ (Apr '24) or Mistral Small (2402)?
Command R+ (Apr '24) and Mistral Small (2402) each win one of the two areas where both have results. Command R+ (Apr '24) wins reasoning; Mistral Small (2402) wins coding.
Which is better for coding?
Mistral Small (2402). 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.