Model Comparison

Command R+ vs Granite 3.3 8B Instruct

Granite 3.3 8B Instruct shows notably better performance in the majority of benchmarks. Command R+ is 1.1x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

Command R+ outperforms in 1 benchmarks (MMLU), while Granite 3.3 8B Instruct is better at 2 benchmarks (GSM8k, TruthfulQA).

Granite 3.3 8B Instruct shows notably better performance in the majority of benchmarks.

Sat Apr 11 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Command R+ costs less

For input processing, Command R+ ($0.25/1M tokens) is 2.0x cheaper than Granite 3.3 8B Instruct ($0.50/1M tokens).

For output processing, Command R+ ($1.00/1M tokens) is 2.0x more expensive than Granite 3.3 8B Instruct ($0.50/1M tokens).

In conclusion, Granite 3.3 8B Instruct is more expensive than Command R+.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Sat Apr 11 2026 • llm-stats.com
Cohere
Command R+
Input tokens$0.25
Output tokens$1.00
Best providerCohere
IBM
Granite 3.3 8B Instruct
Input tokens$0.50
Output tokens$0.50
Best providerReplicate
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

96.0B diff

Command R+ has 96.0B more parameters than Granite 3.3 8B Instruct, making it 1200.0% larger.

Cohere
Command R+
104.0Bparameters
IBM
Granite 3.3 8B Instruct
8.0Bparameters
104.0B
Command R+
8.0B
Granite 3.3 8B Instruct

Context Window

Maximum input and output token capacity

Both models have the same input context window of 128,000 tokens. Command R+ can generate longer responses up to 128,000 tokens, while Granite 3.3 8B Instruct is limited to 8,192 tokens.

Cohere
Command R+
Input128,000 tokens
Output128,000 tokens
IBM
Granite 3.3 8B Instruct
Input128,000 tokens
Output8,192 tokens
Sat Apr 11 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Granite 3.3 8B Instruct supports multimodal inputs, whereas Command R+ does not.

Granite 3.3 8B Instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

Command R+

Text
Images
Audio
Video

Granite 3.3 8B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Command R+ is licensed under CC BY-NC, while Granite 3.3 8B Instruct uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

Command R+

CC BY-NC

Open weights

Granite 3.3 8B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Command R+ was released on 2024-08-30, while Granite 3.3 8B Instruct was released on 2025-04-16.

Granite 3.3 8B Instruct is 8 months newer than Command R+.

Command R+

Aug 30, 2024

1.6 years ago

Granite 3.3 8B Instruct

Apr 16, 2025

12 months ago

7mo newer

Knowledge Cutoff

When training data ends

Granite 3.3 8B Instruct has a documented knowledge cutoff of 2024-04-01, while Command R+'s cutoff date is not specified.

We can confirm Granite 3.3 8B Instruct's training data extends to 2024-04-01, but cannot make a direct comparison without Command R+'s cutoff date.

Command R+

—

Granite 3.3 8B Instruct

Apr 2024

Provider Availability

Command R+ is available from Cohere, Bedrock. Granite 3.3 8B Instruct is available from Replicate.

Command R+

cohere logo
Cohere
Input Price:Input: $0.25/1MOutput Price:Output: $1.00/1M
bedrock logo
AWS Bedrock
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M

Granite 3.3 8B Instruct

replicate logo
Replicate
Input Price:Input: $0.50/1MOutput Price:Output: $0.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Cohere
Less expensive input tokens
Higher MMLU score (75.7% vs 65.5%)
IBM
Supports multimodal inputs
Less expensive output tokens
Higher GSM8k score (80.9% vs 70.7%)
Higher TruthfulQA score (66.9% vs 56.3%)

Detailed Comparison

AI Model Comparison Table
Feature
Cohere
Command R+
IBM
Granite 3.3 8B Instruct

FAQ

Common questions about Command R+ vs Granite 3.3 8B Instruct

Granite 3.3 8B Instruct shows notably better performance in the majority of benchmarks. Command R+ is made by Cohere and Granite 3.3 8B Instruct is made by IBM. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Command R+ scores HellaSwag: 88.6%, Winogrande: 85.4%, MMLU: 75.7%, ARC-C: 71.0%, GSM8k: 70.7%. Granite 3.3 8B Instruct scores HumanEval: 89.7%, AttaQ: 88.5%, HumanEval+: 86.1%, AIME 2024: 81.2%, GSM8k: 80.9%.
Command R+ is 2.0x cheaper for input tokens. Command R+ costs $0.25/M input and $1.00/M output via cohere. Granite 3.3 8B Instruct costs $0.50/M input and $0.50/M output via replicate.
Command R+ supports 128K tokens and Granite 3.3 8B Instruct supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include input pricing ($0.25 vs $0.50/M), multimodal support (no vs yes), licensing (CC BY-NC vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.
Command R+ is developed by Cohere and Granite 3.3 8B Instruct is developed by IBM.