Command R vs Command R+: Benchmark Comparison
Detailed comparison of Command R and Command R+ covering benchmarks, pricing, context window, and compliance.
Key Specifications
| Specification | Command R | Command R+ |
|---|---|---|
| Vendor | cohere | cohere |
| Version | r | r-plus |
| Release Date | 2024-03-11 | 2024-04-04 |
| Context Window | 128000 tokens | 128000 tokens |
| Input Modalities | text | text |
| Output Modalities | text | text |
| License | CC-BY-NC-4.0 | CC-BY-NC-4.0 |
| SOC2 | ✓ | ✓ |
| HIPAA | ✗ | ✗ |
| GDPR | ✓ | ✓ |
| ISO 27001 | ✓ | ✓ |
Benchmark Results
| Benchmark | Command R | Command R+ | Winner |
|---|---|---|---|
| ARC | 93.9 | — | Command R |
| BBH | 78.4 | 66.1 | Command R |
| GPQA | 44 | — | Command R |
| GSM8K | 86.9 | 68.4 | Command R |
| HUMANEVAL | 75.8 | 70.7 | Command R |
| IFEVAL | 74.1 | — | Command R |
| MATH | 43.9 | 35.6 | Command R |
| MMLU | 79.3 | 75 | Command R |
| MUSR | 57 | — | Command R |
| WINOGRANDE | 84.8 | — | Command R |
Pricing Comparison
| Tier (per Mtok) | Command R | Command R+ |
|---|---|---|
| Input | $0.15 | $2.5 |
| Output | $0.6 | $10 |
| Cache Read | $0 | $0 |
| Cache Write | $0 | $0 |
Command R vs Command R+
Model Overview
Command R and Command R+ are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.
Key Specifications
| Vendor | Release Date | Context Window | License |
|---|---|---|---|
| Cohere / Cohere | 2024-03-11 / 2024-04-04 | 128K / 128K | CC-BY-NC-4.0 / CC-BY-NC-4.0 |
Benchmark Performance
| Benchmark | Command R | Command R+ | Winner |
|---|---|---|---|
| ARC | 93.9 | — | A |
| BBH (BIG-Bench Hard) | 78.4 | 66.1 | A |
| GPQA | 44.0 | — | A |
| GSM8K (Grade School Math 8K) | 86.9 | 68.4 | A |
| HumanEval | 75.8 | 70.7 | A |
| IFEval | 74.1 | — | A |
| MATH | 43.9 | 35.6 | A |
| MMLU (Massive Multitask Language Understanding) | 79.3 | 75.0 | A |
| MUSR | 57.0 | — | A |
| WinoGrande | 84.8 | — | A |
Pricing Comparison
| Input | Output | Cache Read | Cache Write |
|---|---|---|---|
| — / — | — / — | — / — | — / — |
per million tokens — A / B
Strengths & Weaknesses
Command R
- ✅ GSM8K 86.9, robust math reasoning.
- ✅ Enterprise-grade compliance.
- ⚠️ Proprietary, not self-hostable.
Command R+
- ✅ Enterprise-grade compliance.
- ⚠️ Proprietary, not self-hostable.
Editor’s Take
Command R and Command R+ each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.
FAQ
Which model is better for coding tasks?
Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.
Which model is cheaper?
Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.
Which has a longer context window?
Refer to the key specifications table; the model with a larger context window is better for long documents.
References
Editor's Take
See Editor's Take section.