Model comparison

Command A vs Mercury 2

Mercury 2 is the stronger model overall, scoring 39.1 to 36.5 on the Noometry Index.

Last verified October 11, 2026. 12 shared benchmarks.

Command A

Cohere

36.5

Rank #215 Confirmed

Mercury 2 Inception

39.1

Rank #175 Confirmed

Summary

They share 12 benchmarks with published results for both. Command A scores higher in 2 categories and Mercury 2 in 5 categories; 5 gaps are clear of the uncertainty.
The widest gap is in coding, where Mercury 2 leads 33.5 to 27.2.
Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2.50 / $10 for Command A.
Command A accepts more context: 256K tokens versus 128K.
Command A has downloadable open weights; the other is API-only.

Side by side

Command A and Mercury 2 specifications
	Command A	Mercury 2
Provider	Cohere	Inception
Noometry Index	36.5	39.1
Released	2025-03-13	2026-02-20
Weights	Open	Proprietary
Context window	256K	128K
Max output	8K	50K
Input $ / M tokens	$2.50	$0.25
Output $ / M tokens	$10	$0.75
Results tracked	24	17

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

Category by category

Coding Mercury 2 leads

Command A: 27.2 (#322), Mercury 2: 33.5 (#255)

Coding benchmarks
Benchmark	Command A	Mercury 2
LMArena Coding	1330	1391
Aider Polyglot	12%	—
LMArena WebDev	—	1171
SciCode	—	38.7%
WeirdML	—	43.2%
ALE-Bench	—	785.58

Agentic & Tool Use Not comparable

Command A: 35.9 (#40), Mercury 2: —

Agentic & Tool Use benchmarks
Benchmark	Command A	Mercury 2
Berkeley Function Calling Leaderboard	57.1%	—

Reasoning Mercury 2 leads

Command A: 18.3 (#283), Mercury 2: 23.8 (#170)

Reasoning benchmarks
Benchmark	Command A	Mercury 2
LMArena Hard Prompts	1326	1362
Kagi LLM Benchmark	28.8%	—
CritPt	—	0.8%
DTBench	61.3%	—
LMCA	10.3%	—

Math Not comparable

Command A: 36.2 (#171), Mercury 2: —

Math benchmarks
Benchmark	Command A	Mercury 2
LMArena Math	1300	—

Knowledge Too close to call

Command A: 37.1 (#159), Mercury 2: 36.2 (#172)

Knowledge benchmarks
Benchmark	Command A	Mercury 2
Vectara Hallucination Rate	9.3%	12.3%
LMArena Expert	1295	1358

Multilingual Mercury 2 leads

Command A: 45.3 (#170), Mercury 2: 46.6 (#157)

Multilingual benchmarks
Benchmark	Command A	Mercury 2
LMArena Non-English	1313	1331
LMArena Chinese	1327	1417
LMArena Russian	1314	1304
LMArena French	1351	—
LMArena German	1341	—
LMArena Japanese	1285	—
LMArena Korean	1285	—
LMArena Spanish	1347	—

Instruction Following Mercury 2 leads

Command A: 69.1 (#177), Mercury 2: 70.2 (#165)

Instruction Following benchmarks
Benchmark	Command A	Mercury 2
LMArena Instruction Following	1309	1329

Long Context Too close to call

Command A: 40.6 (#151), Mercury 2: 40.5 (#154)

Long Context benchmarks
Benchmark	Command A	Mercury 2
LMArena Longer Query	1334	1330

Writing & Preference Mercury 2 leads

Command A: 47.6 (#208), Mercury 2: 53.8 (#155)

Writing & Preference benchmarks
Benchmark	Command A	Mercury 2
LMArena Text	1331	1355
LMArena Creative Writing	1319	1289
LMArena Multi-Turn	1339	1358
EQ-Bench Creative Writing	1145	—

Frequently asked questions

Is Command A better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 39.1 to 36.5 on the Noometry Index.

Which is cheaper, Command A or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Command A lists at $2.50 and $10.

Is Command A or Mercury 2 better for coding?

Mercury 2 scores higher on coding benchmarks: 33.5 versus 27.2 in the Noometry coding category.

Which has the bigger context window?

Command A does, with 256K tokens against 128K.

How many benchmarks do Command A and Mercury 2 share?

12 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Mercury 2 has 17.