The AI arena is free today

Open Superagent

Codestral-22B vs MiniMax M3.1 Flash

MiniMax M3.1 Flash leads the LLM Stats Score 48.5 to -0.3.

Mistral AI · MiniMax · Updated for 2026

Which is better?

MiniMax M3.1 Flash leads the overall LLM Stats Score 48.5 to -0.3, ranking #29 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 MiniMax M3.1 Flash

  • overall performance matters — it scores 48.5 and ranks #29 on LLM Stats
  • your work emphasizes reasoning and coding — 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
MiniMax M3.1 Flash
MiniMax
Core performance indexes
LLM Stats Score
-0.3
#350
48.5
#29
Reasoning
-0.4
#343
45.8
#34
Coding
2.4
#248
37.8
#23
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.15 / M
Output price
— / M
$0.60 / M
Context window
—
1,000,000

Individual benchmarks

7 reported for Codestral-22B · 14 for MiniMax M3.1 Flash

No common benchmarks found

Codestral-22B and MiniMax M3.1 Flashdon'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 MiniMax M3.1 Flash specifies input context (1,000,000 tokens). Only MiniMax M3.1 Flash specifies output context (524,288 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
MiniMax
MiniMax M3.1 Flash
Input1,000,000 tokens
Output524,288 tokens
Tue Oct 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

MiniMax M3.1 Flash supports multimodal inputs, whereas Codestral-22B does not.

MiniMax M3.1 Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

MiniMax M3.1 Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while MiniMax M3.1 Flash 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

MiniMax M3.1 Flash

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while MiniMax M3.1 Flash was released on 2026-10-19.

MiniMax M3.1 Flash is 29 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.4 years ago

MiniMax M3.1 Flash

Oct 19, 2026

0 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 MiniMax M3.1 Flash side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
MiniMax M3.1 Flash
Open in Playground

FAQ

Common questions about Codestral-22B vs MiniMax M3.1 Flash.

Which is better, Codestral-22B or MiniMax M3.1 Flash?

MiniMax M3.1 Flash leads the LLM Stats Score 48.5 to -0.3. Codestral-22B is made by Mistral AI and MiniMax M3.1 Flash is made by MiniMax. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to MiniMax M3.1 Flash in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. MiniMax M3.1 Flash scores BabyVision: 91.0%, CharXiv-R: 82.5%, CyberGym: 82.2%, BankerToolBench: 76.2%, DeepSWE 1.1: 73.7%.

What are the context window sizes for Codestral-22B and MiniMax M3.1 Flash?

Codestral-22B supports an unknown number of tokens and MiniMax M3.1 Flash 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 MiniMax M3.1 Flash?

Key differences include LLM Stats Score (-0.3 vs 48.5), 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 MiniMax M3.1 Flash?

Codestral-22B is developed by Mistral AI and MiniMax M3.1 Flash is developed by MiniMax.

Related comparisons