Noometry

Model comparison

Command R vs Llama 3-8B

Command R is the stronger model overall, scoring 31.0 to 25.3 on the Noometry Index. Llama 3-8B costs 1.9× less per token, which makes it the better buy when Command R's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

Command R Cohere

31.0

Rank #267 Confirmed

Llama 3-8B Meta

25.3

Rank #338 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Command R scores higher in 5 categories and Llama 3-8B in 3 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Command R leads 30.5 to 7.8.
  • The biggest single-benchmark swing is BigCodeBench Complete: 45.2% for Command R and 36.9% for Llama 3-8B.
  • Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $0.15 / $0.60 for Command R.
  • Command R accepts more context: 128K tokens versus 8K.

Side by side

Command RLlama 3-8B
ProviderCohereMeta
Noometry Index31.025.3
Released2024-08-302024-04-18
WeightsOpenOpen
Context window128K8K
Max output4K8K
Input $ / M tokens$0.15$0.14
Output $ / M tokens$0.60$0.14
Results tracked2934

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

Category by category

Coding Llama 3-8B leads

Command R: 28.8 (#301), Llama 3-8B: 30.5 (#285)

BenchmarkCommand RLlama 3-8B
BigCodeBench Instruct37.1%31.9%
LMArena Coding11701152
BigCodeBench Complete45.2%36.9%
LiveBench Coding17.9%—
HumanEval+—56.7%
MBPP+—54.8%

Reasoning Too close to call

Command R: 13.3 (#329), Llama 3-8B: 13.8 (#321)

BenchmarkCommand RLlama 3-8B
LMArena Hard Prompts11641133
DTBench46.4%43.9%
Chess Puzzles—0%
LiveBench Reasoning21.9%—
LiveBench Data Analysis33.3%—
LMCA9.2%—
Adversarial NLI—57.3%
Epoch Capabilities Index—116.33
ForecastBench—58.6
LiveBench27.5%—
WinoGrande—75.7%

Math Command R leads

Command R: 25.8 (#244), Llama 3-8B: 8.3 (#317)

BenchmarkCommand RLlama 3-8B
LMArena Math11551151
OTIS Mock AIME 2024-2025—1.9%
LiveBench Math19.4%—
MATH Level 5—6.1%

Knowledge Command R leads

Command R: 30.5 (#219), Llama 3-8B: 7.8 (#303)

BenchmarkCommand RLlama 3-8B
LMArena Expert11381113
MMLU65.2%68.8%
GPQA Diamond—26.1%
ARC (AI2) Challenge—82.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multilingual Command R leads

Command R: 35.9 (#240), Llama 3-8B: 31.0 (#256)

BenchmarkCommand RLlama 3-8B
LMArena Non-English11741098
LMArena Chinese11821076
LMArena French11611158
LMArena German11761104
LMArena Japanese1143967
LMArena Korean11621003
LMArena Russian11741109
LMArena Spanish11501172

Instruction Following Too close to call

Command R: 58.3 (#256), Llama 3-8B: 58.7 (#255)

BenchmarkCommand RLlama 3-8B
LMArena Instruction Following11671127
LiveBench Instruction Following55.6%—

Long Context Command R leads

Command R: 36.3 (#226), Llama 3-8B: 34.2 (#246)

BenchmarkCommand RLlama 3-8B
LMArena Longer Query11981128

Writing & Preference Too close to call

Command R: 38.4 (#248), Llama 3-8B: 37.7 (#251)

BenchmarkCommand RLlama 3-8B
LMArena Text11871166
LMArena Creative Writing11701150
LMArena Multi-Turn11631152
LiveBench Language16.7%—

Frequently asked questions

Is Command R better than Llama 3-8B?

Command R is the stronger model overall, scoring 31.0 to 25.3 on the Noometry Index. Llama 3-8B costs 1.9× less per token, which makes it the better buy when Command R's lead doesn't matter for your workload.

Which is cheaper, Command R or Llama 3-8B?

Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; Command R lists at $0.15 and $0.60.

Is Command R or Llama 3-8B better for coding?

Llama 3-8B scores higher on coding benchmarks: 30.5 versus 28.8 in the Noometry coding category.

Which has the bigger context window?

Command R does, with 128K tokens against 8K.

How many benchmarks do Command R and Llama 3-8B share?

21 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper