Command R (08-2024)
Aug 2024
Command R (08-2024)Compare inon
Benchmarks of Command R (08-2024)14
BenchmarkByScoreRank
No benchmark matches
Rankingconfiguration unstated?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 FlashunstatedOpenwins 83%-33%$0.14 / $0.28Pass back reasoning_content+3
BetterGPT-5 Minihighwins 74%+162%$0.053OpenMiMo v2.6 Prounstatedwins 85%+107%$0.43 / $0.87Pass back reasoning_content+3
CheaperGLM 5.3 FlashunstatedOpenwins 83%-10%$0.15 / $0.50Defaults to max · Self-hosted+4
CheaperGemma 4 31BunstatedOpenwins 81%-39%$0.10 / $0.34ModelScoreCostPer taskWhat changes
MiMo v2.6 FlashunstatedOpenwins 83%-33%$0.14 / $0.28Pass back reasoning_content+3GLM 5.3 FlashunstatedOpenwins 83%-10%$0.15 / $0.50Defaults to max · Self-hosted+4Gemma 4 31BunstatedOpenwins 81%-39%$0.10 / $0.34
Hy3unstatedOpenwins 81%-12%$0.13 / $0.53MiMo v2.5unstatedOpenwins 81%-33%$0.14 / $0.28ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 74%+162%$0.053GPT-6 Lunamaxwins 76%-24%$0.068Function calling only with none · Chat Completions+3
Claude Haiku 5.5highwins 77%-24%$0.079Remove sampling parameters+5GPT-5.6 Lunaxhighwins 80%+71%$0.085GPT-5.6 Terraxhighwins 81%+1,614%$0.63Prompts with >272K input tokensModelScoreCostPer taskWhat changes
MiMo v2.6 ProunstatedOpenwins 85%+107%$0.43 / $0.87Pass back reasoning_content+3GLM 5.3maxOpenwins 84%+719%$2.01Reasoning cannot be disabled+3
Kimi K3maxOpenwins 84%+2,186%$2.00Sampling parameters are fixed+3MiMo v2.5 ProunstatedOpenwins 83%+107%$0.43 / $0.87GLM 5.1unstatedOpenwins 83%+719%$1.40 / $4.40ModelScoreCostPer taskWhat changes
Command AunstatedOpenwins 70%—$2.50 / $10Command R+ (08-2024)unstatedOpenwins 56%—$2.50 / $10Command R+Openwins 52%——Command ROpenwins 47%——North Mini CodeOpenn/a——Command A+thinkingOpenn/a—$0.30 / $1.50Tiny Aya GlobalOpenn/a——Context: 128K → 8K+1Command R7B (12-2024)Openn/a—$0.037 / $0.15All Cohere models →Run it yourself
Fits onhardware needs not verified yet
Licencenot verified
History
2 versionsBenchmarks
all categoriesChat & Knowledge
Arena Text · overall1,251#176
Arena Text · Chinese1,182.3#180
Arena Text · English1,197.7#187
Arena Text · German1,176.2#148
Arena Text · instruction following1,167#185
Arena Text · Japanese1,143.2#132
Arena Text · Korean1,162.4#135
Arena Text · non-English1,174.2#185
Arena Text · Russian1,173.7#183
Arena Text · overall · October 22, 20261,187.3#178
Arena Text · overall · October 15, 20261,187.3#169
Writing & Language
Arena Text · creative writing1,209#172
FAQ
How much does Command R (08-2024) cost?›
$0.15 per 1M input tokens and $0.60 per 1M output tokens.
Is Command R (08-2024) free to use?›
There is no free API; the cheapest paid price is $0.15 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Command R (08-2024), and what is it best at?›
#187 of 205 in Chat & Knowledge, #176 of 197 in Writing & Language.
Is Command R (08-2024) better than Command R+?›
On Arena Text · English, Command R (08-2024) scores 1,197.7 vs 1,213.1 — lower.
How can I use Command R (08-2024)?›
Through the API of Cohere.
What is the context window of Command R (08-2024)?›
128K tokens, with up to 4K output tokens.
When was Command R (08-2024) released? Is there a newer version?›
Released 2024-08-30. It is the current version in its line.
Is Command R (08-2024) open source?›
Yes, the weights are open.
Can I run Command R (08-2024) locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Command R (08-2024) read images?›
No, it accepts text only.
What is Command R (08-2024)?›
Command R (08-2024) is an open-weights language model from Cohere, released Aug 2024.
What are the best alternatives to Command R (08-2024)?›
MiMo v2.6 Flash (cheaper), GPT-5 Mini (better), MiMo v2.6 Pro (open weights).