Noometry

Cohere, open weights

Command R

Command R by Cohere ranks 272nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.4. Its strongest category is knowledge, where it ranks 221st. API pricing starts at $0.15 per million input tokens and $0.60 per million output tokens, with a 128K-token context window.

Last verified

Noometry rank
#272 of 354
Index score
31.4
Evidence
Confirmed 29 results
Provider
Cohere
Released
August 30, 2024
Weights
Open weights
Reasoning
No
Context window
128K
Max output
4K
Input price
$0.15 / M
Output price
$0.60 / M
Blended price
$0.26 / M
Output speed
Not measured
Value
#53 of 219
Knowledge cutoff
June 2024
Input
text

Category scores

Each category score combines every public result we have in that category.

  1. Coding 29.3
  2. Reasoning 13.8
  3. Math 28.0
  4. Knowledge 31.0
  5. Multilingual 35.7
  6. Instruction Following 58.1
  7. Long Context 36.3
  8. Writing & Preference 38.2
CategoryScoreRankResults
Coding29.3#3064
Reasoning13.8#3315
Math28.0#2462
Knowledge31.0#2211
Multilingual35.7#2451
Instruction Following58.1#2612
Long Context36.3#2311
Writing & Preference38.2#2544

Strengths and weaknesses

Categories where Command R places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Knowledge31.0−6.3#221 of 314, top 71%
Math28.0−8.6#246 of 327, top 76%
Long Context36.3−4.6#231 of 296, top 79%

Weakest categories

CategoryScorevs medianRank
Reasoning13.8−9.8#331 of 350, top 95%
Coding29.3−9.4#306 of 340, top 90%
Instruction Following58.1−13.2#261 of 305, top 86%

Closest competitors

The models ranked just above and below Command R. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Llama2 70b Steerlm Chat#26831.8——Compare
Mistral Small 3.1#26931.7$0.40—Compare
Granite 3.0 8b Instruct#27031.6——Compare
o1-pro#27131.5$263—Compare
Qwen1.5-7B#27331.4——Compare
Wizardlm 13b#27431.4——Compare
Qwen-14B#27531.4——Compare
Phi 3 Mini 4k Instruct June 2024#27631.3——Compare

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

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
BigCodeBench Instruct37.1%#42 of 64, top 66%BigCodeBench2024-08-30
LiveBench Coding17.9%#37 of 39, top 95%Epoch AI
LMArena Coding1169#250 of 294, top 86%LMArena2026-10-08
LMArena Coding1128LMArena2026-10-08
BigCodeBench Complete45.2%#43 of 66, top 66%BigCodeBench2024-08-30

Reasoning

BenchmarkScorePositionSettingSourceDate
LiveBench Reasoning21.9%#36 of 39, top 93%Epoch AI
LMArena Hard Prompts1115LMArena2026-10-08
LMArena Hard Prompts1164#250 of 297, top 85%LMArena2026-10-08
DTBench46.4%#144 of 151, top 96%Epoch AI
LiveBench Data Analysis33.3%#37 of 39, top 95%Epoch AI
LMCA9.2%#114 of 125, top 92%Epoch AI
LiveBench27.5%#36 of 39, top 93%Epoch AI

Math

BenchmarkScorePositionSettingSourceDate
LiveBench Math19.4%#36 of 39, top 93%Epoch AI
LMArena Math1120LMArena2026-10-08
LMArena Math1155#248 of 285, top 88%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert1138#242 of 273, top 89%LMArena2026-10-08
LMArena Expert1108LMArena2026-10-08
MMLU65.2%#55 of 81, top 68%Epoch AI

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1144LMArena2026-10-08
LMArena Non-English1174#245 of 297, top 83%LMArena2026-10-08
LMArena Chinese1182#239 of 285, top 84%LMArena2026-10-08
LMArena Chinese1146LMArena2026-10-08
LMArena French1162#202 of 223, top 91%LMArena2026-10-08
LMArena German1128LMArena2026-10-08
LMArena German1176#197 of 231, top 86%LMArena2026-10-08
LMArena Japanese1094LMArena2026-10-08
LMArena Japanese1143#178 of 211, top 85%LMArena2026-10-08
LMArena Korean1092LMArena2026-10-08
LMArena Korean1163#174 of 213, top 82%LMArena2026-10-08
LMArena Russian1158LMArena2026-10-08
LMArena Russian1174#244 of 283, top 87%LMArena2026-10-08
LMArena Spanish1151#204 of 226, top 91%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LiveBench Instruction Following55.6%#34 of 39, top 88%Epoch AI
LMArena Instruction Following1167#248 of 298, top 84%LMArena2026-10-08
LMArena Instruction Following1125LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1158LMArena2026-10-08
LMArena Longer Query1198#241 of 291, top 83%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1163LMArena2026-10-08
LMArena Text1187#248 of 297, top 84%LMArena2026-10-08
LMArena Creative Writing1154LMArena2026-10-08
LMArena Creative Writing1170#245 of 295, top 84%LMArena2026-10-08
LMArena Multi-Turn1147LMArena2026-10-08
LMArena Multi-Turn1163#247 of 295, top 84%LMArena2026-10-08
LiveBench Language16.7%#35 of 39, top 90%Epoch AI

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
cohere$0.15$0.60—2026-10-10
openrouter$0.15$0.60—2026-10-10

All Cohere API prices → Estimate your cost →

Compare Command R

Other Cohere models

Frequently asked questions

How good is Command R?

Command R by Cohere ranks 272nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.4. Its strongest category is knowledge, where it ranks 221st. API pricing starts at $0.15 per million input tokens and $0.60 per million output tokens, with a 128K-token context window.

How much does Command R cost?

Command R costs $0.15 per million input tokens and $0.60 per million output tokens on Cohere's own API.

What is Command R's context window?

Command R accepts up to 128K tokens of input and can write up to 4K tokens in one response.

Is Command R open source?

Yes. Command R's weights are downloadable; check the license for commercial terms.

What are Command R's strengths and weaknesses?

Relative to other ranked models, Command R places best in knowledge, math, long context and lowest in reasoning, coding, instruction following.

What is Command R best at?

Its best category is knowledge, where it ranks 221st on Noometry.