Noometry

Model comparison

Command R+ vs DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 32.4 on the Noometry Index.

Last verified . 9 shared benchmarks.

Command R+ Cohere

32.4

Rank #257 Confirmed

DeepSeek-R1-Distill-Llama-70B DeepSeek

37.8

Rank #195 Confirmed

Summary

  • They share 9 benchmarks with published results for both. Command R+ scores higher in 1 category and DeepSeek-R1-Distill-Llama-70B in 5 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek-R1-Distill-Llama-70B leads 24.9 to 9.2.
  • The biggest single-benchmark swing is LiveBench Reasoning: 24.8% for Command R+ and 67.6% for DeepSeek-R1-Distill-Llama-70B.

Side by side

Command R+DeepSeek-R1-Distill-Llama-70B
ProviderCohereDeepSeek
Noometry Index32.437.8
Released2024-08-302025-01-20
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$2.50—
Output $ / M tokens$10—
Results tracked3413

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

Category by category

Coding DeepSeek-R1-Distill-Llama-70B leads

Command R+: 29.1 (#309), DeepSeek-R1-Distill-Llama-70B: 36.8 (#202)

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
BigCodeBench Instruct33.8%35.3%
LiveBench Coding19.1%51.6%
BigCodeBench Complete41.9%49.9%
LMArena Coding1187—
HumanEval+56.7%—
MBPP+63.5%—

Reasoning DeepSeek-R1-Distill-Llama-70B leads

Command R+: 9.2 (#344), DeepSeek-R1-Distill-Llama-70B: 24.9 (#156)

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
LiveBench Reasoning24.8%67.6%
LiveBench Data Analysis38.1%55.9%
LiveBench31.8%54.5%
SimpleBench17.4%—
Kagi LLM Benchmark—52.3%
LMArena Hard Prompts1186—
DTBench54.9%—
LMCA5%—
Epoch Capabilities Index119.34—

Math DeepSeek-R1-Distill-Llama-70B leads

Command R+: 28.9 (#242), DeepSeek-R1-Distill-Llama-70B: 36.0 (#176)

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
LiveBench Math21.3%58.1%
OTIS Mock AIME 2024-2025—51.4%
LMArena Math1188—
MATH Level 5—89.9%

Knowledge Command R+ leads

Command R+: 36.4 (#169), DeepSeek-R1-Distill-Llama-70B: 30.7 (#225)

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
GPQA Diamond—55.7%
Vectara Hallucination Rate6.9%—
LMArena Expert1174—
MMLU69.4%—

Multilingual Not comparable

Command R+: 38.6 (#227), DeepSeek-R1-Distill-Llama-70B: —

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
LMArena Non-English1216—
LMArena Chinese1226—
LMArena French1209—
LMArena German1216—
LMArena Japanese1166—
LMArena Korean1138—
LMArena Russian1227—
LMArena Spanish1189—

Instruction Following DeepSeek-R1-Distill-Llama-70B leads

Command R+: 60.0 (#254), DeepSeek-R1-Distill-Llama-70B: 68.2 (#190)

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
LiveBench Instruction Following57.6%69.9%
LMArena Instruction Following1197—

Long Context Not comparable

Command R+: 37.3 (#219), DeepSeek-R1-Distill-Llama-70B: —

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
LMArena Longer Query1230—

Writing & Preference DeepSeek-R1-Distill-Llama-70B leads

Command R+: 43.5 (#228), DeepSeek-R1-Distill-Llama-70B: 49.0 (#194)

BenchmarkCommand R+DeepSeek-R1-Distill-Llama-70B
LiveBench Language29.7%23.8%
LMArena Text1229—
LMArena Creative Writing1235—
LMArena Multi-Turn1213—

Frequently asked questions

Is Command R+ better than DeepSeek-R1-Distill-Llama-70B?

DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 32.4 on the Noometry Index.

Is Command R+ or DeepSeek-R1-Distill-Llama-70B better for coding?

DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.8 versus 29.1 in the Noometry coding category.

How many benchmarks do Command R+ and DeepSeek-R1-Distill-Llama-70B share?

9 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and DeepSeek-R1-Distill-Llama-70B has 13.

Related comparisons

Go deeper