Model comparison

Command A vs Mistral Medium 3.1

Command A is the stronger model overall, scoring 36.5 to 31.9 on the Noometry Index. Mistral Medium 3.1 costs 5.5× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.

Last verified October 11, 2026. 1 shared benchmarks.

Command A

Cohere

36.5

Rank #215 Confirmed

Mistral Medium 3.1

Mistral AI

31.9

Rank #266 Reported

Summary

They share 1 benchmark with published results for both. Command A scores higher in 1 category and Mistral Medium 3.1 in 1 category; 2 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Mistral Medium 3.1 leads 55.5 to 47.6.
Mistral Medium 3.1 is cheaper at $0.40 / $2 per million input/output tokens, against $2.50 / $10 for Command A.
Command A accepts more context: 256K tokens versus 131K.
Command A has downloadable open weights; the other is API-only.

Side by side

Command A and Mistral Medium 3.1 specifications
	Command A	Mistral Medium 3.1
Provider	Cohere	Mistral AI
Noometry Index	36.5	31.9
Released	2025-03-13	—
Weights	Open	Proprietary
Context window	256K	131K
Max output	8K	105K
Input $ / M tokens	$2.50	$0.40
Output $ / M tokens	$10	$2
Results tracked	24	3

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

Category by category

Coding Not comparable

Command A: 27.2 (#322), Mistral Medium 3.1: —

Coding benchmarks
Benchmark	Command A	Mistral Medium 3.1
Aider Polyglot	12%	—
LMArena Coding	1330	—

Agentic & Tool Use Not comparable

Command A: 35.9 (#40), Mistral Medium 3.1: —

Agentic & Tool Use benchmarks
Benchmark	Command A	Mistral Medium 3.1
Berkeley Function Calling Leaderboard	57.1%	—

Reasoning Command A leads

Command A: 18.3 (#283), Mistral Medium 3.1: 10.6 (#341)

Reasoning benchmarks
Benchmark	Command A	Mistral Medium 3.1
Kagi LLM Benchmark	28.8%	—
NYT Connections (extended)	—	6.5%
Thematic Generalization	—	20.3%
LMArena Hard Prompts	1326	—
DTBench	61.3%	—
LMCA	10.3%	—

Math Not comparable

Command A: 36.2 (#171), Mistral Medium 3.1: —

Math benchmarks
Benchmark	Command A	Mistral Medium 3.1
LMArena Math	1300	—

Knowledge Not comparable

Command A: 37.1 (#159), Mistral Medium 3.1: —

Knowledge benchmarks
Benchmark	Command A	Mistral Medium 3.1
Vectara Hallucination Rate	9.3%	—
LMArena Expert	1295	—

Multilingual Not comparable

Command A: 45.3 (#170), Mistral Medium 3.1: —

Multilingual benchmarks
Benchmark	Command A	Mistral Medium 3.1
LMArena Non-English	1313	—
LMArena Chinese	1327	—
LMArena French	1351	—
LMArena German	1341	—
LMArena Japanese	1285	—
LMArena Korean	1285	—
LMArena Russian	1314	—
LMArena Spanish	1347	—

Instruction Following Not comparable

Command A: 69.1 (#177), Mistral Medium 3.1: —

Instruction Following benchmarks
Benchmark	Command A	Mistral Medium 3.1
LMArena Instruction Following	1309	—

Long Context Not comparable

Command A: 40.6 (#151), Mistral Medium 3.1: —

Long Context benchmarks
Benchmark	Command A	Mistral Medium 3.1
LMArena Longer Query	1334	—

Writing & Preference Mistral Medium 3.1 leads

Command A: 47.6 (#208), Mistral Medium 3.1: 55.5 (#145)

Writing & Preference benchmarks
Benchmark	Command A	Mistral Medium 3.1
EQ-Bench Creative Writing	1145	1476
LMArena Text	1331	—
LMArena Creative Writing	1319	—
LMArena Multi-Turn	1339	—

Frequently asked questions

Is Command A better than Mistral Medium 3.1?

Which is cheaper, Command A or Mistral Medium 3.1?

Mistral Medium 3.1 is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; Command A lists at $2.50 and $10.

Which has the bigger context window?

Command A does, with 256K tokens against 131K.

How many benchmarks do Command A and Mistral Medium 3.1 share?

1 benchmark has published results for both models. Command A has 24 scored results on Noometry and Mistral Medium 3.1 has 3.