The AI arena is free today

Open Superagent

Codestral-22B vs Inkling 2 Small

Inkling 2 Small leads the LLM Stats Score 47.2 to -0.5.

Mistral AI · Thinking Machines Lab · Updated for 2026

Which is better?

Inkling 2 Small leads the overall LLM Stats Score 47.2 to -0.5, ranking #39 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 Inkling 2 Small

  • overall performance matters — it scores 47.2 and ranks #39 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you want the most recent training data — it shipped Nov 2026

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Inkling 2 Small
Thinking Machines Lab
Core performance indexes
LLM Stats Score
-0.5
#369
47.2
#39
Reasoning
-0.7
#360
47.9
#24
Coding
2.3
#263
36.3
#35
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.30 / M
Output price
— / M
$1.00 / M
Context window
—
256,000

Individual benchmarks

7 reported for Codestral-22B · 11 for Inkling 2 Small

No common benchmarks found

Codestral-22B and Inkling 2 Smalldon'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

Model Size

Parameter count comparison

571.8B diff

Inkling 2 Small has 571.8B more parameters than Codestral-22B, making it 2575.7% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Thinking Machines Lab
Inkling 2 Small
594.0Bparameters
22.2B
Codestral-22B
594.0B
Inkling 2 Small

Context Window

Maximum input and output token capacity

Only Inkling 2 Small specifies input context (256,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Thinking Machines Lab
Inkling 2 Small
Input256,000 tokens
Output- tokens
Mon Nov 09 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Inkling 2 Small supports multimodal inputs, whereas Codestral-22B does not.

Inkling 2 Small can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Inkling 2 Small

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Inkling 2 Small 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

Inkling 2 Small

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Inkling 2 Small was released on 2026-11-05.

Inkling 2 Small is 30 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.4 years ago

Inkling 2 Small

Nov 5, 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 Inkling 2 Small side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Inkling 2 Small
Open in Playground

FAQ

Common questions about Codestral-22B vs Inkling 2 Small.

Which is better, Codestral-22B or Inkling 2 Small?

Inkling 2 Small leads the LLM Stats Score 47.2 to -0.5. Codestral-22B is made by Mistral AI and Inkling 2 Small is made by Thinking Machines Lab. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Inkling 2 Small in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Inkling 2 Small scores GPQA: 93.0%, BrowseComp: 90.2%, CharXiv-R: 85.6%, MCP Atlas: 85.0%, SWE-Bench Verified: 82.2%.

What are the context window sizes for Codestral-22B and Inkling 2 Small?

Codestral-22B supports an unknown number of tokens and Inkling 2 Small supports 256K 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 Inkling 2 Small?

Key differences include LLM Stats Score (-0.5 vs 47.2), 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 Inkling 2 Small?

Codestral-22B is developed by Mistral AI and Inkling 2 Small is developed by Thinking Machines Lab.

Related comparisons