DBRX Instruct wins more areas, narrowly.
Scores updated · 16 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 DBRX Instruct pulls ahead
- Code for real scientific research problemsSciCode+5.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+4.7points ahead
Where Command R pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.9points ahead
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.
ReasoningEven
- GPQA DiamondDBRX Instruct by 4.728.433.1+4.7
- Humanity's Last ExamCommand R by 1.94.82.9+1.9
Other results13 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.
- simple_safety_testsCommand R by 40.894.353.5+40.8
- NarrativeQACommand R by 25.474.248.8+25.4
- HarmBenchCommand R by 23.350.427.1+23.3
- anthropic_red_teamCommand R by 17.193.776.6+17.1
- XSTestCommand R by 16.593.977.4+16.5
- OpenBookQADBRX Instruct by 12.878.291+12.8
- GSM8KDBRX Instruct by 1255.167.1+12
- MATHDBRX Instruct by 9.226.635.8+9.2
- MMLUDBRX Instruct by 7.656.764.3+7.6
- bbqDBRX Instruct by 6.872.479.2+6.8
- naturalquestions_closedbookCommand R by 6.835.228.4+6.8
- AIR-Bench 2024Command R by 6.431.825.4+6.4
- AA Intelligencetie55.3tie
Questions people ask
Which is better, Command R or DBRX Instruct?
DBRX Instruct 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?
DBRX Instruct. It wins the one coding test both models report.
How do you compare the two?
We use the 16 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 13 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.