Noometry

Model comparison

Command R+ vs Llama 2-70B

Command R+ is the stronger model overall, scoring 32.4 to 24.4 on the Noometry Index.

Last verified . 20 shared benchmarks.

Command R+ Cohere

32.4

Rank #257 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Command R+ scores higher in 6 categories and Llama 2-70B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Command R+ leads 36.4 to 7.4.
  • The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 41.6% for Llama 2-70B.

Side by side

Command R+Llama 2-70B
ProviderCohereMeta
Noometry Index32.424.4
Released2024-08-302023-07-18
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$2.50—
Output $ / M tokens$10—
Results tracked3435

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Llama 2-70B leads

Command R+: 29.1 (#309), Llama 2-70B: 31.4 (#286)

BenchmarkCommand R+Llama 2-70B
LMArena Coding11871079
BigCodeBench Instruct33.8%—
LiveBench Coding19.1%—
BigCodeBench Complete41.9%—
HumanEval+56.7%—
MBPP+63.5%—

Reasoning Llama 2-70B leads

Command R+: 9.2 (#344), Llama 2-70B: 14.4 (#325)

BenchmarkCommand R+Llama 2-70B
LMArena Hard Prompts11861073
DTBench54.9%41.6%
Epoch Capabilities Index119.34113.79
SimpleBench17.4%—
LiveBench Reasoning24.8%—
LiveBench Data Analysis38.1%—
LMCA5%—
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
LiveBench31.8%—
PIQA—82.8%
WinoGrande—80.2%

Math Command R+ leads

Command R+: 28.9 (#242), Llama 2-70B: 8.1 (#326)

BenchmarkCommand R+Llama 2-70B
LMArena Math11881091
OTIS Mock AIME 2024-2025—0%
LiveBench Math21.3%—
MATH Level 5—3.3%
GSM8K—69.6%

Knowledge Command R+ leads

Command R+: 36.4 (#169), Llama 2-70B: 7.4 (#310)

BenchmarkCommand R+Llama 2-70B
LMArena Expert11741039
MMLU69.4%69.9%
GPQA Diamond—26.3%
Vectara Hallucination Rate6.9%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
OpenBookQA—60.2%
TriviaQA—87.6%

Multilingual Command R+ leads

Command R+: 38.6 (#227), Llama 2-70B: 27.7 (#274)

BenchmarkCommand R+Llama 2-70B
LMArena Non-English12161045
LMArena Chinese1226995
LMArena French12091090
LMArena German12161041
LMArena Japanese1166927
LMArena Korean1138964
LMArena Russian12271083
LMArena Spanish11891143

Instruction Following Command R+ leads

Command R+: 60.0 (#254), Llama 2-70B: 54.9 (#278)

BenchmarkCommand R+Llama 2-70B
LMArena Instruction Following11971071
LiveBench Instruction Following57.6%—

Long Context Command R+ leads

Command R+: 37.3 (#219), Llama 2-70B: 32.3 (#270)

BenchmarkCommand R+Llama 2-70B
LMArena Longer Query12301062

Writing & Preference Command R+ leads

Command R+: 43.5 (#228), Llama 2-70B: 32.3 (#279)

BenchmarkCommand R+Llama 2-70B
LMArena Text12291115
LMArena Creative Writing12351075
LMArena Multi-Turn12131088
LiveBench Language29.7%—

Frequently asked questions

Is Command R+ better than Llama 2-70B?

Command R+ is the stronger model overall, scoring 32.4 to 24.4 on the Noometry Index.

Is Command R+ or Llama 2-70B better for coding?

Llama 2-70B scores higher on coding benchmarks: 31.4 versus 29.1 in the Noometry coding category.

How many benchmarks do Command R+ and Llama 2-70B share?

20 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper