Noometry

Model comparison

Command R+ vs Phi 3 Small 8k Instruct

Command R+ is the stronger model overall, scoring 32.4 to 29.3 on the Noometry Index.

Last verified . 25 shared benchmarks.

Command R+ Cohere

32.4

Rank #257 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Command R+ scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Command R+ leads 43.5 to 31.1.
  • The biggest single-benchmark swing is LiveBench Language: 29.7% for Command R+ and 12.9% for Phi 3 Small 8k Instruct.

Side by side

Command R+Phi 3 Small 8k Instruct
ProviderCohereMicrosoft
Noometry Index32.429.3
Released2024-08-302024-04-23
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$2.50—
Output $ / M tokens$10—
Results tracked3432

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

Category by category

Coding Command R+ leads

Command R+: 29.1 (#309), Phi 3 Small 8k Instruct: 27.9 (#318)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LiveBench Coding19.1%20.3%
LMArena Coding11871101
BigCodeBench Instruct33.8%—
BigCodeBench Complete41.9%—
HumanEval+56.7%—
MBPP+63.5%—

Reasoning Phi 3 Small 8k Instruct leads

Command R+: 9.2 (#344), Phi 3 Small 8k Instruct: 14.8 (#323)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LiveBench Reasoning24.8%15.9%
LMArena Hard Prompts11861100
LiveBench Data Analysis38.1%30.3%
LiveBench31.8%24%
SimpleBench17.4%—
DTBench54.9%—
LMCA5%—
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
Epoch Capabilities Index119.34—
HellaSwag—77%
WinoGrande—81.5%

Math Command R+ leads

Command R+: 28.9 (#242), Phi 3 Small 8k Instruct: 27.6 (#248)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LiveBench Math21.3%17.6%
LMArena Math11881151

Knowledge Command R+ leads

Command R+: 36.4 (#169), Phi 3 Small 8k Instruct: 29.1 (#240)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LMArena Expert11741067
MMLU69.4%75.7%
Vectara Hallucination Rate6.9%—
ARC (AI2) Challenge—90.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual Command R+ leads

Command R+: 38.6 (#227), Phi 3 Small 8k Instruct: 28.5 (#272)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LMArena Non-English12161058
LMArena Chinese12261061
LMArena French12091135
LMArena German12161080
LMArena Japanese1166966
LMArena Korean1138894
LMArena Russian12271111
LMArena Spanish11891111

Instruction Following Command R+ leads

Command R+: 60.0 (#254), Phi 3 Small 8k Instruct: 51.9 (#292)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LiveBench Instruction Following57.6%47.2%
LMArena Instruction Following11971087

Long Context Command R+ leads

Command R+: 37.3 (#219), Phi 3 Small 8k Instruct: 33.0 (#267)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LMArena Longer Query12301088

Writing & Preference Command R+ leads

Command R+: 43.5 (#228), Phi 3 Small 8k Instruct: 31.1 (#284)

BenchmarkCommand R+Phi 3 Small 8k Instruct
LMArena Text12291110
LMArena Creative Writing12351083
LMArena Multi-Turn12131068
LiveBench Language29.7%12.9%

Frequently asked questions

Is Command R+ better than Phi 3 Small 8k Instruct?

Command R+ is the stronger model overall, scoring 32.4 to 29.3 on the Noometry Index.

Is Command R+ or Phi 3 Small 8k Instruct better for coding?

Command R+ scores higher on coding benchmarks: 29.1 versus 27.9 in the Noometry coding category.

How many benchmarks do Command R+ and Phi 3 Small 8k Instruct share?

25 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper