Noometry

Model comparison

Command R vs DeepSeek-V3.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.4 on the Noometry Index. Command R costs 1.6× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

Command R Cohere

31.4

Rank #272 Confirmed

DeepSeek-V3.1 DeepSeek

42.8

Rank #108 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Command R scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 38.2.
  • The biggest single-benchmark swing is DTBench: 46.4% for Command R and 82.7% for DeepSeek-V3.1.
  • Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
  • DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.

Side by side

Command RDeepSeek-V3.1
ProviderCohereDeepSeek
Noometry Index31.442.8
Released2024-08-302025-08-21
WeightsOpenOpen
Context window128K164K
Max output4K8K
Input $ / M tokens$0.15$0.25
Output $ / M tokens$0.60$0.95
Results tracked2927

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

Category by category

Coding DeepSeek-V3.1 leads

Command R: 29.3 (#306), DeepSeek-V3.1: 40.3 (#144)

BenchmarkCommand RDeepSeek-V3.1
LMArena Coding11691417
WeirdML—38.4%
BigCodeBench Instruct37.1%—
LiveBench Coding17.9%—
BigCodeBench Complete45.2%—

Reasoning DeepSeek-V3.1 leads

Command R: 13.8 (#331), DeepSeek-V3.1: 27.9 (#110)

BenchmarkCommand RDeepSeek-V3.1
LMArena Hard Prompts11641417
DTBench46.4%82.7%
LMCA9.2%24.3%
SimpleBench—40%
Kagi LLM Benchmark—53.2%
LiveBench Reasoning21.9%—
LiveBench Data Analysis33.3%—
Epoch Capabilities Index—139.92
ForecastBench—58
LiveBench27.5%—

Math DeepSeek-V3.1 leads

Command R: 28.0 (#246), DeepSeek-V3.1: 38.9 (#122)

BenchmarkCommand RDeepSeek-V3.1
LMArena Math11551420
LiveBench Math19.4%—

Knowledge DeepSeek-V3.1 leads

Command R: 31.0 (#221), DeepSeek-V3.1: 43.7 (#90)

BenchmarkCommand RDeepSeek-V3.1
LMArena Expert11381405
Vectara Hallucination Rate—5.5%
MMLU65.2%—

Multilingual DeepSeek-V3.1 leads

Command R: 35.7 (#245), DeepSeek-V3.1: 51.6 (#106)

BenchmarkCommand RDeepSeek-V3.1
LMArena Non-English11741400
LMArena Chinese11821469
LMArena French11621447
LMArena German11761411
LMArena Japanese11431378
LMArena Korean11631337
LMArena Russian11741405
LMArena Spanish11511431

Instruction Following DeepSeek-V3.1 leads

Command R: 58.1 (#261), DeepSeek-V3.1: 73.9 (#110)

BenchmarkCommand RDeepSeek-V3.1
LMArena Instruction Following11671400
LiveBench Instruction Following55.6%—

Long Context Too close to call

Command R: 36.3 (#231), DeepSeek-V3.1: 36.3 (#232)

BenchmarkCommand RDeepSeek-V3.1
LMArena Longer Query11981422
Fiction.LiveBench—52.8%

Writing & Preference DeepSeek-V3.1 leads

Command R: 38.2 (#254), DeepSeek-V3.1: 60.3 (#98)

BenchmarkCommand RDeepSeek-V3.1
LMArena Text11871420
LMArena Creative Writing11701401
LMArena Multi-Turn11631408
EQ-Bench Creative Writing—1436
LiveBench Language16.7%—

Frequently asked questions

Is Command R better than DeepSeek-V3.1?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.4 on the Noometry Index. Command R costs 1.6× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

Which is cheaper, Command R or DeepSeek-V3.1?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

Is Command R or DeepSeek-V3.1 better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 29.3 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 128K.

How many benchmarks do Command R and DeepSeek-V3.1 share?

19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek-V3.1 has 27.

Related comparisons

Go deeper