The AI arena is free today

Open Superagent

Codestral-22B vs Particle-1

Particle-1 leads the LLM Stats Score 31.9 to -0.4.

Mistral AI · Particle AI · Updated for 2026

Which is better?

Particle-1 leads the overall LLM Stats Score 31.9 to -0.4, ranking #133 overall.

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

Choose Codestral-22B

  • you need open weights you can self-host or fine-tune

Choose Particle-1

  • overall performance matters — it scores 31.9 and ranks #133 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Particle-1
Particle AI
Core performance indexes
LLM Stats Score
-0.4
#363
31.9
#133
Reasoning
-0.5
#356
31.2
#135
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.25 / M
Output price
— / M
$1.00 / M
Context window
—
1,048,576

Individual benchmarks

7 reported for Codestral-22B · 3 for Particle-1

No common benchmarks found

Codestral-22B and Particle-1don'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

Context Window

Maximum input and output token capacity

Only Particle-1 specifies input context (1,048,576 tokens). Only Particle-1 specifies output context (131,072 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Particle AI
Particle-1
Input1,048,576 tokens
Output131,072 tokens
Fri Oct 30 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Particle-1 supports multimodal inputs, whereas Codestral-22B does not.

Particle-1 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Particle-1

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Particle-1 uses a proprietary license.

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

Codestral-22B

MNPL-0.1

Open weights

Particle-1

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Particle-1 was released on 2026-10-28.

Particle-1 is 29 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.4 years ago

Particle-1

Oct 28, 2026

-3 days ago

2.4yr 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

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Codestral-22B and Particle-1 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Particle-1
Open in Playground

FAQ

Common questions about Codestral-22B vs Particle-1.

Which is better, Codestral-22B or Particle-1?

Particle-1 leads the LLM Stats Score 31.9 to -0.4. Codestral-22B is made by Mistral AI and Particle-1 is made by Particle AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Particle-1 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Particle-1 scores GPQA: 90.4%, BabyVision: 89.2%, MMLU: 86.1%.

What are the context window sizes for Codestral-22B and Particle-1?

Codestral-22B supports an unknown number of tokens and Particle-1 supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Codestral-22B and Particle-1?

Key differences include LLM Stats Score (-0.4 vs 31.9), multimodal support (no vs yes), licensing (MNPL-0.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Particle-1?

Codestral-22B is developed by Mistral AI and Particle-1 is developed by Particle AI.

Related comparisons