Command R+ vs Llama 3.2 90B Instruct
Command R+ and Llama 3.2 90B Instruct are closely matched at -0.2 and 5.3 on the LLM Stats Score. Llama 3.2 90B Instruct is 1.2x cheaper per token.
Cohere · Meta · Updated for 2026
Which is better?
Command R+ and Llama 3.2 90B Instruct are closely matched on the overall LLM Stats Score at -0.2 and 5.3.
In the 1 individual benchmarks reported for both models, Llama 3.2 90B Instruct wins 1; this is a narrower head-to-head signal than the composite indexes.
On price, Llama 3.2 90B Instruct is roughly 1.2x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Command R+
- you want predictable pricing at $0.25/M input and $1.00/M output
Choose Llama 3.2 90B Instruct
- you value its reported benchmark strengths — it wins 1 of 1 exact shared results
- cost matters — it's about 1.2x cheaper per token
- you want the most recent training data — it shipped Sep 2024
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
6 reported for Command R+ · 13 for Llama 3.2 90B Instruct
Command R+ outperforms in 0 benchmarks, while Llama 3.2 90B Instruct is better at 1 benchmark (MMLU).
Llama 3.2 90B Instruct significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Command R+ ($0.25/1M tokens) is 1.4x cheaper than Llama 3.2 90B Instruct ($0.35/1M tokens).
For output processing, Command R+ ($1.00/1M tokens) is 2.5x more expensive than Llama 3.2 90B Instruct ($0.40/1M tokens).
In conclusion, Command R+ is more expensive than Llama 3.2 90B Instruct.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Command R+ has 14.0B more parameters than Llama 3.2 90B Instruct, making it 15.6% larger.
Context Window
Maximum input and output token capacity
Both models have the same input context window of 128,000 tokens. Both models can generate responses up to 128,000 tokens.
Input capabilities
Documented input modalities across available providers
Llama 3.2 90B Instruct supports multimodal inputs, whereas Command R+ does not.
Llama 3.2 90B Instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.
Command R+
Llama 3.2 90B Instruct
License
Usage and distribution terms
Command R+ is licensed under CC BY-NC, while Llama 3.2 90B Instruct uses Llama 3.2.
License differences may affect how you can use these models in commercial or open-source projects.
CC BY-NC
Open weights
Llama 3.2
Open weights
Release Timeline
When each model was launched
Command R+ was released on 2024-08-30, while Llama 3.2 90B Instruct was released on 2024-09-25.
Llama 3.2 90B Instruct is 1 month newer than Command R+.
Aug 30, 2024
2.0 years ago
Sep 25, 2024
1.9 years ago
3w newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Command R+ is available from Cohere, Bedrock. Llama 3.2 90B Instruct is available from DeepInfra, Bedrock, Fireworks, Together, Hyperbolic.
Command R+
Llama 3.2 90B Instruct
Outputs Comparison
Judge for yourself.
Run your own prompts against Command R+ and Llama 3.2 90B Instruct side-by-side, then vote on the output you prefer.
FAQ
Common questions about Command R+ vs Llama 3.2 90B Instruct.