Noometry

Model comparison

Command R+ vs Mercury 2

Mercury 2 is the stronger model overall, scoring 39.1 to 32.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

Command R+ Cohere

32.4

Rank #257 Confirmed

Mercury 2 Inception

39.1

Rank #175 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Command R+ scores higher in 1 category and Mercury 2 in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Mercury 2 leads 23.8 to 9.2.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 6.9% for Command R+ and 12.3% for Mercury 2.
  • Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2.50 / $10 for Command R+.
  • Command R+ has downloadable open weights; the other is API-only.

Side by side

Command R+Mercury 2
ProviderCohereInception
Noometry Index32.439.1
Released2024-08-302026-02-20
WeightsOpenProprietary
Context window128K128K
Max output4K50K
Input $ / M tokens$2.50$0.25
Output $ / M tokens$10$0.75
Results tracked3417

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

Category by category

Coding Mercury 2 leads

Command R+: 29.1 (#309), Mercury 2: 33.5 (#255)

BenchmarkCommand R+Mercury 2
LMArena Coding11871391
LMArena WebDev—1171
SciCode—38.7%
WeirdML—43.2%
BigCodeBench Instruct33.8%—
LiveBench Coding19.1%—
BigCodeBench Complete41.9%—
ALE-Bench—785.58
HumanEval+56.7%—
MBPP+63.5%—

Reasoning Mercury 2 leads

Command R+: 9.2 (#344), Mercury 2: 23.8 (#170)

BenchmarkCommand R+Mercury 2
LMArena Hard Prompts11861362
SimpleBench17.4%—
CritPt—0.8%
LiveBench Reasoning24.8%—
DTBench54.9%—
LiveBench Data Analysis38.1%—
LMCA5%—
Epoch Capabilities Index119.34—
LiveBench31.8%—

Math Not comparable

Command R+: 28.9 (#242), Mercury 2: —

BenchmarkCommand R+Mercury 2
LiveBench Math21.3%—
LMArena Math1188—

Knowledge Too close to call

Command R+: 36.4 (#169), Mercury 2: 36.2 (#172)

BenchmarkCommand R+Mercury 2
Vectara Hallucination Rate6.9%12.3%
LMArena Expert11741358
MMLU69.4%—

Multilingual Mercury 2 leads

Command R+: 38.6 (#227), Mercury 2: 46.6 (#157)

BenchmarkCommand R+Mercury 2
LMArena Non-English12161331
LMArena Chinese12261417
LMArena Russian12271304
LMArena French1209—
LMArena German1216—
LMArena Japanese1166—
LMArena Korean1138—
LMArena Spanish1189—

Instruction Following Mercury 2 leads

Command R+: 60.0 (#254), Mercury 2: 70.2 (#165)

BenchmarkCommand R+Mercury 2
LMArena Instruction Following11971329
LiveBench Instruction Following57.6%—

Long Context Mercury 2 leads

Command R+: 37.3 (#219), Mercury 2: 40.5 (#154)

BenchmarkCommand R+Mercury 2
LMArena Longer Query12301330

Writing & Preference Mercury 2 leads

Command R+: 43.5 (#228), Mercury 2: 53.8 (#155)

BenchmarkCommand R+Mercury 2
LMArena Text12291355
LMArena Creative Writing12351289
LMArena Multi-Turn12131358
LiveBench Language29.7%—

Frequently asked questions

Is Command R+ better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 39.1 to 32.4 on the Noometry Index.

Which is cheaper, Command R+ or Mercury 2?

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

Is Command R+ or Mercury 2 better for coding?

Mercury 2 scores higher on coding benchmarks: 33.5 versus 29.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 128K tokens.

How many benchmarks do Command R+ and Mercury 2 share?

12 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Mercury 2 has 17.

Related comparisons

Go deeper