Noometry

Model comparison

Command R+ vs Qwen Max

Qwen Max is the stronger model overall, scoring 34.7 to 32.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Command R+ Cohere

32.4

Rank #257 Confirmed

Qwen Max Alibaba (Qwen)

34.7

Rank #230 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Command R+ scores higher in 2 categories and Qwen Max in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen Max leads 25.1 to 9.2.
  • Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $2.50 / $10 for Command R+.
  • Command R+ accepts more context: 128K tokens versus 33K.
  • Command R+ has downloadable open weights; the other is API-only.

Side by side

Command R+Qwen Max
ProviderCohereAlibaba (Qwen)
Noometry Index32.434.7
Released2024-08-302024-04-03
WeightsOpenProprietary
Context window128K33K
Max output4K8K
Input $ / M tokens$2.50$1.60
Output $ / M tokens$10$6.40
Results tracked3423

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

Category by category

Coding Qwen Max leads

Command R+: 29.1 (#309), Qwen Max: 30.7 (#292)

BenchmarkCommand R+Qwen Max
LMArena Coding11871288
Aider Polyglot—21.8%
BigCodeBench Instruct33.8%—
LiveBench Coding19.1%—
BigCodeBench Complete41.9%—
HumanEval+56.7%—
MBPP+63.5%—

Reasoning Qwen Max leads

Command R+: 9.2 (#344), Qwen Max: 25.1 (#151)

BenchmarkCommand R+Qwen Max
LMArena Hard Prompts11861269
SimpleBench17.4%—
LiveBench Reasoning24.8%—
DTBench54.9%—
LiveBench Data Analysis38.1%—
LMCA5%—
Epoch Capabilities Index119.34—
LiveBench31.8%—

Math Command R+ leads

Command R+: 28.9 (#242), Qwen Max: 22.3 (#276)

BenchmarkCommand R+Qwen Max
LMArena Math11881275
OTIS Mock AIME 2024-2025—16.1%
LiveBench Math21.3%—
MATH Level 5—67.2%
FrontierMath (Feb 2025 set)—1%

Knowledge Command R+ leads

Command R+: 36.4 (#169), Qwen Max: 30.3 (#228)

BenchmarkCommand R+Qwen Max
LMArena Expert11741248
GPQA Diamond—56.1%
Vectara Hallucination Rate6.9%—
MMLU69.4%—

Multilingual Qwen Max leads

Command R+: 38.6 (#227), Qwen Max: 41.8 (#202)

BenchmarkCommand R+Qwen Max
LMArena Non-English12161263
LMArena Chinese12261254
LMArena French12091330
LMArena German12161254
LMArena Japanese11661205
LMArena Korean11381142
LMArena Russian12271274
LMArena Spanish11891290

Instruction Following Qwen Max leads

Command R+: 60.0 (#254), Qwen Max: 66.5 (#208)

BenchmarkCommand R+Qwen Max
LMArena Instruction Following11971262
LiveBench Instruction Following57.6%—

Long Context Qwen Max leads

Command R+: 37.3 (#219), Qwen Max: 39.4 (#180)

BenchmarkCommand R+Qwen Max
LMArena Longer Query12301288
Fiction.LiveBench—66.7%

Writing & Preference Qwen Max leads

Command R+: 43.5 (#228), Qwen Max: 47.8 (#205)

BenchmarkCommand R+Qwen Max
LMArena Text12291282
LMArena Creative Writing12351248
LMArena Multi-Turn12131277
LiveBench Language29.7%—

Frequently asked questions

Is Command R+ better than Qwen Max?

Qwen Max is the stronger model overall, scoring 34.7 to 32.4 on the Noometry Index.

Which is cheaper, Command R+ or Qwen Max?

Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; Command R+ lists at $2.50 and $10.

Is Command R+ or Qwen Max better for coding?

Qwen Max scores higher on coding benchmarks: 30.7 versus 29.1 in the Noometry coding category.

Which has the bigger context window?

Command R+ does, with 128K tokens against 33K.

How many benchmarks do Command R+ and Qwen Max share?

17 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Qwen Max has 23.

Related comparisons

Go deeper