Language modelActive
Command R7B
Cohere
- Released
- December 2024
- Data date
- September 8, 2026
- Price
- Input · Output / 1M tokens
- Input
- Text
- Output
- Text
Command R7B is the smallest checkpoint in Cohere's Command R family and pairs 23 languages with a clearly documented RAG focus. The 128,000-token context therefore comes with a 4,000-token maximum output.
Cohere lists the checkpoint as live and releases the weights under CC-BY-NC-4.0. That license rules out unrestricted commercial deployment. On long answers or demanding reasoning tasks, the output cap remains the limiting detail.
Specifications and access
| Specification | Value and source |
|---|---|
| Weights | Open weightsSource |
| Access | API, LocalSource |
| Parameters | 7BSource |
| Context window | 128,000 tokensSource |
| Knowledge cutoff | June 1, 2024Source |
| Notes | Smallest Command R model, with a 128K context window.Source |
| License | CC-BY-NC-4.0Source |
| Release | 2024-12-13Source |
| Parameters | 7 BSource |
| Architecture | auto-regressive transformerSource |
| Maximum output | 4,000 tokensSource |
| Input | TextSource |
| Output | TextSource |
| Languages | 23Source |
| Tool calling | YesSource |
| Structured output | YesSource |
Page 1 of 2
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
MMLU (Show measurement, test conditions, and source)
- Source value
- 65.2
- Score
- 65.2
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
MMLU-Pro (Show measurement, test conditions, and source)
- Source value
- 42.4
- Score
- 42.4
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
GPQA (Show measurement, test conditions, and source)
- Source value
- 26.3
- Score
- 26.3
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
IFEval (Show measurement, test conditions, and source)
- Source value
- 77.9
- Score
- 77.9
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
InFoBench (Show measurement, test conditions, and source)
- Source value
- 85.6
- Score
- 85.6
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
MATH (Show measurement, test conditions, and source)
- Source value
- 59.1
- Score
- 59.1
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
BFCL (Show measurement, test conditions, and source)
- Source value
- 52.2
- Score
- 52.2
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
MBPP+ (Show measurement, test conditions, and source)
- Source value
- 72
- Score
- 72
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
Bird-SQL (Show measurement, test conditions, and source)
- Source value
- 42.2
- Score
- 42.2
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
RepoQA (Show measurement, test conditions, and source)
- Source value
- 69.6
- Score
- 69.6
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
NTREX (Show measurement, test conditions, and source)
- Source value
- 48.1
- Score
- 48.1
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
SWE-Bench Verified (Show measurement, test conditions, and source)
- Source value
- 3.6
- Score
- 3.6
- Metric
- percent
- Unit
- %
- Category
- academic/code/enterprise
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Command A technical report
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Table 3/1; BF16 or report default; exact shots and metrics in report
- Context
- Canonical index ID command-r7b maps to API model command-r7b-12-2024; official inventory lists 2024-12-02, release changelog lists 2024-12-13.
Page 1 of 2
Popularity
29.6 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Price | Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. |
| Input | Documented modalities. Retrieved September 8, 2026. |
| Output | Documented modalities. Retrieved September 8, 2026. |
| Research status | Research date September 8, 2026. 5 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | training-tokens Original wording Checked docs, release changelog and model card do not publish a training-token count. |
| Unresolved | AA benchmark rows Original wording No exact Artificial Analysis model page located in the checked public sitemap. |
| Additional source | Context window data |
| Additional source | Knowledge cutoff data (retrieved September 8, 2026) · Cohere Command R7B model documentation · Editorial description reviewed October 2, 2026 |
| Additional source | Cohere Command A technical report (retrieved September 8, 2026) |
| Additional source | Model metadata (retrieved September 8, 2026) · Cohere Command R7B release note · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |