Command R+ (Apr '24) vs Llama 3.1 Instruct 405B
Wins 0 of 2 areas
—
Wins 2 of 2 areas
Coding · Reasoning
Llama 3.1 Instruct 405B is the stronger all-rounder.
Scores updated · 20 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 Llama 3.1 Instruct 405B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+19.2points ahead
- Code for real scientific research problemsSciCode+18.1points ahead
- Common-sense trick questionsSimpleBench+5.6points ahead
Where Command R+ (Apr '24) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningLlama 3.1 Instruct 405B
- GPQA DiamondLlama 3.1 Instruct 405B by 19.232.351.5+19.2
- SimpleBenchLlama 3.1 Instruct 405B by 5.617.423+5.6
- Humanity's Last Examtie4.64tie
Other results16 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.
- MATHLlama 3.1 Instruct 405B by 33.540.373.8+33.5
- MMLULlama 3.1 Instruct 405B by 29.65988.6+29.6
- AIR-Bench 2024Llama 3.1 Instruct 405B by 29.329.358.6+29.3
- GSM8KLlama 3.1 Instruct 405B by 26.170.796.8+26.1
- ARC-ChallengeLlama 3.1 Instruct 405B by 25.97196.9+25.9
- HarmBenchLlama 3.1 Instruct 405B by 14.248.562.7+14.2
- naturalquestions_closedbookLlama 3.1 Instruct 405B by 11.334.345.6+11.3
- OpenBookQALlama 3.1 Instruct 405B by 11.282.894+11.2
- bbqLlama 3.1 Instruct 405B by 4.689.994.5+4.6
- XSTestLlama 3.1 Instruct 405B by 2.193.895.9+2.1
- AA IntelligenceLlama 3.1 Instruct 405B by 25.37.3+2
- anthropic_red_teamCommand R+ (Apr '24) by 1.59896.5+1.5
- NarrativeQALlama 3.1 Instruct 405B by 1.473.574.9+1.4
- simple_safety_testsCommand R+ (Apr '24) by 1.210098.8+1.2
- HellaSwagtie88.689.2tie
- WinoGrandetie85.485.2tie
Questions people ask
Which is better, Command R+ (Apr '24) or Llama 3.1 Instruct 405B?
Llama 3.1 Instruct 405B wins all two areas where both have results: coding and reasoning. Command R+ (Apr '24) wins none.
Which is better for coding?
Llama 3.1 Instruct 405B. It wins the one coding test both models report.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.