The AI arena is free today

Open Superagent

Command R+ vs DeepSeek-V3 0324

DeepSeek-V3 0324 leads the LLM Stats Score 13.7 to -0.1. Command R+ is 1.1x cheaper per token.

Cohere · DeepSeek · Updated for 2026

Which is better?

DeepSeek-V3 0324 leads the overall LLM Stats Score 13.7 to -0.1, ranking #229 overall.

On price, Command R+ is roughly 1.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

DeepSeek-V3 0324 also accepts a larger context window (163,840 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Command R+

  • cost matters — it's about 1.1x cheaper per token

Choose DeepSeek-V3 0324

  • overall performance matters — it scores 13.7 and ranks #229 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you process long inputs — it offers a 163,840 token context window
  • you want the most recent training data — it shipped Mar 2025

At a glance

The differences that matter most.

Command R+
Cohere
DeepSeek-V3 0324
DeepSeek
Core performance indexes
LLM Stats Score
-0.1
#310
13.7
#229
Reasoning
-0.4
#306
13.9
#219
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.25 / M
$0.28 / M
Output price
$1.00 / M
$1.14 / M
Context window
128,000
163,840

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Command R+
DeepSeek-V3 0324
Math
-1.7#297
16.1#200
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

6 reported for Command R+ · 5 for DeepSeek-V3 0324

No common benchmarks found

Command R+ and DeepSeek-V3 0324don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Command R+ costs less

For input processing, Command R+ ($0.25/1M tokens) is 1.1x cheaper than DeepSeek-V3 0324 ($0.28/1M tokens).

For output processing, Command R+ ($1.00/1M tokens) is 1.1x cheaper than DeepSeek-V3 0324 ($1.14/1M tokens).

In conclusion, DeepSeek-V3 0324 is more expensive than Command R+.*

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

Lowest available price from all providers
Tue Sep 01 2026 • llm-stats.com
Cohere
Command R+
Input tokens$0.25
Output tokens$1.00
Best providerCohere
DeepSeek
DeepSeek-V3 0324
Input tokens$0.28
Output tokens$1.14
Best providerNovita
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

567.0B diff

DeepSeek-V3 0324 has 567.0B more parameters than Command R+, making it 545.2% larger.

Cohere
Command R+
104.0Bparameters
DeepSeek
DeepSeek-V3 0324
671.0Bparameters
104.0B
Command R+
671.0B
DeepSeek-V3 0324

Context Window

Maximum input and output token capacity

DeepSeek-V3 0324 accepts 163,840 input tokens compared to Command R+'s 128,000 tokens. DeepSeek-V3 0324 can generate longer responses up to 163,840 tokens, while Command R+ is limited to 128,000 tokens.

Cohere
Command R+
Input128,000 tokens
Output128,000 tokens
DeepSeek
DeepSeek-V3 0324
Input163,840 tokens
Output163,840 tokens
Tue Sep 01 2026 • llm-stats.com

License

Usage and distribution terms

Command R+ is licensed under CC BY-NC, while DeepSeek-V3 0324 uses MIT + Model License (Commercial use allowed).

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

Command R+

CC BY-NC

Open weights

DeepSeek-V3 0324

MIT + Model License (Commercial use allowed)

Open weights

Release Timeline

When each model was launched

Command R+ was released on 2024-08-30, while DeepSeek-V3 0324 was released on 2025-03-25.

DeepSeek-V3 0324 is 7 months newer than Command R+.

Command R+

Aug 30, 2024

2.0 years ago

DeepSeek-V3 0324

Mar 25, 2025

1.4 years ago

6mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Command R+ is available from Cohere, Bedrock. DeepSeek-V3 0324 is available from Novita.

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

DeepSeek-V3 0324

novita logo
Novita
Input Price:Input: $0.28/1MOutput Price:Output: $1.14/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Command R+ and DeepSeek-V3 0324 side-by-side, then vote on the output you prefer.

Command R+
✓ Preferred
DeepSeek-V3 0324
Open in Playground

FAQ

Common questions about Command R+ vs DeepSeek-V3 0324.

Which is better, Command R+ or DeepSeek-V3 0324?

DeepSeek-V3 0324 leads the LLM Stats Score 13.7 to -0.1. Command R+ is made by Cohere and DeepSeek-V3 0324 is made by DeepSeek. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Command R+ compare to DeepSeek-V3 0324 in benchmarks?

Command R+ scores HellaSwag: 88.6%, Winogrande: 85.4%, MMLU: 75.7%, ARC-C: 71.0%, GSM8k: 70.7%. DeepSeek-V3 0324 scores MATH-500: 94.0%, MMLU-Pro: 81.2%, GPQA: 68.4%, AIME 2024: 59.4%, LiveCodeBench: 49.2%.

Is Command R+ cheaper than DeepSeek-V3 0324?

Command R+ is 1.1x cheaper for input tokens. Command R+ costs $0.25/M input and $1.00/M output via cohere. DeepSeek-V3 0324 costs $0.28/M input and $1.14/M output via novita.

What are the context window sizes for Command R+ and DeepSeek-V3 0324?

Command R+ supports 128K tokens and DeepSeek-V3 0324 supports 164K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Command R+ and DeepSeek-V3 0324?

Key differences include LLM Stats Score (-0.1 vs 13.7), context window (128K vs 164K), input pricing ($0.25 vs $0.28/M), licensing (CC BY-NC vs MIT + Model License (Commercial use allowed)). See the full comparison above for benchmark-by-benchmark results.

Who makes Command R+ and DeepSeek-V3 0324?

Command R+ is developed by Cohere and DeepSeek-V3 0324 is developed by DeepSeek.

Related comparisons