Model comparison

Command R vs Ministral 3B

Command R is the stronger model overall, scoring 31.4 to 26.2 on the Noometry Index. Ministral 3B costs 2.6× less per token, which makes it the better buy when Command R's lead doesn't matter for your workload.

Last verified . 2 shared benchmarks.

Command R Cohere

31.4

Rank #272 Confirmed

Ministral 3B Mistral AI

26.2

Rank #338 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Command R scores higher in 2 categories and Ministral 3B in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Command R leads 31.0 to 10.4.
  • The biggest single-benchmark swing is DTBench: 46.4% for Command R and 51.7% for Ministral 3B.
  • Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.15 / $0.60 for Command R.
  • Ministral 3B accepts more context: 131K tokens versus 128K.

Side by side

Command R and Ministral 3B specifications
Command RMinistral 3B
ProviderCohereMistral AI
Noometry Index31.426.2
Released2024-08-302024-10-01
WeightsOpenOpen
Context window128K131K
Max output4K262K
Input $ / M tokens$0.15$0.10
Output $ / M tokens$0.60$0.10
Results tracked296

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

Category by category

Coding Not comparable

Command R: 29.3 (#306), Ministral 3B: —

Coding benchmarks
BenchmarkCommand RMinistral 3B
BigCodeBench Instruct37.1%—
LiveBench Coding17.9%—
LMArena Coding1169—
BigCodeBench Complete45.2%—

Reasoning Ministral 3B leads

Command R: 13.8 (#331), Ministral 3B: 18.4 (#282)

Reasoning benchmarks
BenchmarkCommand RMinistral 3B
DTBench46.4%51.7%
LMCA9.2%5.5%
LiveBench Reasoning21.9%—
LMArena Hard Prompts1164—
LiveBench Data Analysis33.3%—
Epoch Capabilities Index—118.1
LiveBench27.5%—

Math Command R leads

Command R: 28.0 (#246), Ministral 3B: 26.6 (#258)

Math benchmarks
BenchmarkCommand RMinistral 3B
LiveBench Math19.4%—
LMArena Math1155—
MATH Level 5—14.4%

Knowledge Command R leads

Command R: 31.0 (#221), Ministral 3B: 10.4 (#302)

Knowledge benchmarks
BenchmarkCommand RMinistral 3B
GPQA Diamond—25.3%
Vectara Hallucination Rate—7.3%
LMArena Expert1138—
MMLU65.2%—

Multilingual Not comparable

Command R: 35.7 (#245), Ministral 3B: —

Multilingual benchmarks
BenchmarkCommand RMinistral 3B
LMArena Non-English1174—
LMArena Chinese1182—
LMArena French1162—
LMArena German1176—
LMArena Japanese1143—
LMArena Korean1163—
LMArena Russian1174—
LMArena Spanish1151—

Instruction Following Not comparable

Command R: 58.1 (#261), Ministral 3B: —

Instruction Following benchmarks
BenchmarkCommand RMinistral 3B
LiveBench Instruction Following55.6%—
LMArena Instruction Following1167—

Long Context Not comparable

Command R: 36.3 (#231), Ministral 3B: —

Long Context benchmarks
BenchmarkCommand RMinistral 3B
LMArena Longer Query1198—

Writing & Preference Not comparable

Command R: 38.2 (#254), Ministral 3B: —

Writing & Preference benchmarks
BenchmarkCommand RMinistral 3B
LMArena Text1187—
LMArena Creative Writing1170—
LMArena Multi-Turn1163—
LiveBench Language16.7%—

Frequently asked questions

Is Command R better than Ministral 3B?

Command R is the stronger model overall, scoring 31.4 to 26.2 on the Noometry Index. Ministral 3B costs 2.6× 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 Ministral 3B?

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Command R lists at $0.15 and $0.60.

Which has the bigger context window?

Ministral 3B does, with 131K tokens against 128K.

How many benchmarks do Command R and Ministral 3B share?

2 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Ministral 3B has 6.

Related comparisons

Go deeper