Command-R (Mar '24)
CohereCommand
Release Date
2024-03-12
Parameters
—
Context Length
128K
Modalities
text
Capability Radar
12
general
5
coding
11
reasoning
16
scienceest.
80
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 473 | 5.0 | AA |
| General Ranking | 495 | 13.0 | AA |
| Math Reasoning | 344 | 6.0 | AA |
| Science | 486 | 13.0 | AA |
Benchmark Scores (LLM Stats)
Agents
Cohere Agentic Question Answering
65.0%SR
Cohere Memory Usage Quality
54.0%SR
Cohere Data Analysis
45.0%SR
Terminal-Bench Hard
25.0%SR
Biology
SciCode
38.0%SR
Communication
Tau2 Telecom
85.0%SR
General
MMMU
75.1%SR
IFBench
74.0%SR
MMMU-Pro
63.0%SR
Language
MT-AIME 2025
86.0%SR
WMT24++
81.0%SR
Math
AIME 2025
90.0%SR
MathVista
80.6%SR
Multimodal
CharXiv-D
88.0%SR
CharXiv-R
52.7%SR
AA Evaluation Indices
Intelligence Index2.1
Mmlu Pro0.3
Gpqa0.3
Math 5000.2
Scicode0.1
Hle0.0
Livecodebench0.0
Aime0.0
LLM Stats Category Scores
Structured Output90
Language80
Healthcare80
Communication80
Tool Calling80
Instruction Following70
Math70
Multimodal70
Reasoning70
General70
Vision70
Physics40
Biology40
Chemistry40
Code40
Pricing
Input Price$0.5 / 1M tokens
Output Price$1.5 / 1M tokens
Blended Price (3:1)$0.75 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1Cohere
$0.15
$0.6
Compare pricing across different API providers for this model.