Command R+
Apr 2024
Command R+Compare inon
Benchmarks of Command R+18
BenchmarkByScoreRank
Knowledge17
Health & law1
No benchmark matches
—per task?
price not verifiedprice
—output speed?
128Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5 Minihighwins 62%—$0.053
OpenGemma 4 31Bunstatedwins 74%—$0.10 / $0.34BetterGPT-6 Lunamaxwins 73%—$0.068Function calling only with none · Chat Completions+3BetterGPT-5.6 Lunaxhighwins 73%—$0.085BetterGPT-5.6 Terraxhighwins 75%—$0.63Prompts with >272K input tokensModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 62%—$0.053GPT-6 Lunamaxwins 73%—$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 73%—$0.085GPT-5.6 Terraxhighwins 75%—$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 78%—$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Gemma 4 31BunstatedOpenwins 74%—$0.10 / $0.34
Mistral Medium 3.5unstatedOpenwins 72%—$1.50 / $7.50Memory (4-bit): 62 GB → 77 GBGemma 4 26B A4BunstatedOpenwins 72%—$0.15 / $0.60
Qwen3 235B A22B Thinking 2507unstatedOpenwins 68%—$0.23 / $2.30Memory (4-bit): 62 GB → 141 GB+1Qwen3.8 27BunstatedOpenwins 68%—$0.42 / $2.55max_tokens range · QwenCloud+4ModelScoreCostPer taskWhat changes
Command AunstatedOpenwins 64%—$2.50 / $10Memory (4-bit): 62 GB → 67 GBCommand R+ (08-2024)unstatedOpenwins 54%—$2.50 / $10Memory (4-bit): not verifiedCommand R (08-2024)unstatedOpenwins 46%—$0.15 / $0.60Memory (4-bit): not verifiedCommand ROpenwins 44%——North Mini CodeOpenn/a——Command A+thinkingOpenn/a—$0.30 / $1.50Memory (4-bit): 62 GB → 131 GBTiny Aya GlobalOpenn/a——Context: 128K → 8K+1Command R7B (12-2024)Openn/a—$0.037 / $0.15Memory (4-bit): not verifiedAll Cohere models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✓ 80 GB GPU · compressed
LicenceCC BY-NC 4.0no commercial use
History
2 versionsBenchmarks
all categoriesChat & Knowledge
Arena Text · overall1,262#173
Arena Text · Chinese1,191.1#178
Arena Text · English1,213.1#186
Arena Text · French1,208.8#146
Arena Text · German1,195.5#143
Arena Text · instruction following1,179.6#183
Arena Text · Japanese1,154.7#129
Arena Text · Korean1,137.8#141
Arena Text · non-English1,189.4#180
Arena Text · Polish1,238.4#133
Arena Text · Russian1,205.8#176
Arena Text · Spanish1,189.1#155
Vals LegalBench68.3#83
Arena Text · overall · October 22, 20261,203.8#175
Arena Text · overall · October 15, 20261,203.8#166
Writing & Language
Arena Text · creative writing1,236#167
FAQ
How much does Command R+ cost?›
There is no per-unit API price: price not verified.
How good is Command R+, and what is it best at?›
#186 of 205 in Chat & Knowledge, #170 of 197 in Writing & Language.
Is Command R+ better than Nemotron 4 340B Instruct?›
On Arena Text · creative writing, Command R+ scores 1,236 vs 1,238 — about the same.
What is the context window of Command R+?›
128K tokens.
When was Command R+ released? Is there a newer version?›
Released 2024-04-03. It is the current version in its line.
Is Command R+ open source?›
Yes, the weights are open (cc-by-nc-4.0 licence).
Can I run Command R+ locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Command R+ read images?›
No, it accepts text only.
What is Command R+?›
Command R+ is an open-weights language model from Cohere, released Apr 2024.
What are the best alternatives to Command R+?›
GPT-5 Mini (better), Gemma 4 31B (open weights).