Model Comparison

Codestral-22B vs Phi-3.5-MoE-instructWhich is better in 2026?

Both models are evenly matched across the benchmarks.

Verdict: Codestral-22B vs Phi-3.5-MoE-instruct — which is better?

Codestral-22B (by Mistral AI) and Phi-3.5-MoE-instruct (by Microsoft) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Codestral-22B outperforms in 1 benchmarks (HumanEval), while Phi-3.5-MoE-instruct is better at 1 benchmark (MBPP). Both models are evenly matched across the benchmarks.

Choose Codestral-22B if…

  • you are already invested in the Mistral AI ecosystem

Choose Phi-3.5-MoE-instruct if…

  • you want the most recent training data — it shipped Aug 2024
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

Codestral-22B outperforms in 1 benchmarks (HumanEval), while Phi-3.5-MoE-instruct is better at 1 benchmark (MBPP).

Both models are evenly matched across the benchmarks.

Tue Jun 23 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

37.8B diff

Phi-3.5-MoE-instruct has 37.8B more parameters than Codestral-22B, making it 170.3% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Microsoft
Phi-3.5-MoE-instruct
60.0Bparameters
22.2B
Codestral-22B
60.0B
Phi-3.5-MoE-instruct

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Phi-3.5-MoE-instruct uses MIT.

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

Codestral-22B

MNPL-0.1

Open weights

Phi-3.5-MoE-instruct

MIT

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Phi-3.5-MoE-instruct was released on 2024-08-23.

Phi-3.5-MoE-instruct is 3 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.1 years ago

Phi-3.5-MoE-instruct

Aug 23, 2024

1.8 years ago

2mo 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?Start an Issue discussion→

Key Takeaways

Mistral AI
Higher HumanEval score (81.1% vs 70.7%)
Microsoft
Higher MBPP score (80.8% vs 78.2%)

Detailed Comparison

AI Model Comparison Table
Feature
Mistral AI
Codestral-22B
Microsoft
Phi-3.5-MoE-instruct

FAQ

Common questions about Codestral-22B vs Phi-3.5-MoE-instruct.

Which is better, Codestral-22B or Phi-3.5-MoE-instruct?

Both models are evenly matched across the benchmarks. Codestral-22B is made by Mistral AI and Phi-3.5-MoE-instruct is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Codestral-22B compare to Phi-3.5-MoE-instruct in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Phi-3.5-MoE-instruct scores ARC-C: 91.0%, OpenBookQA: 89.6%, GSM8k: 88.7%, PIQA: 88.6%, RULER: 87.1%.

What are the main differences between Codestral-22B and Phi-3.5-MoE-instruct?

Key differences include licensing (MNPL-0.1 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Phi-3.5-MoE-instruct?

Codestral-22B is developed by Mistral AI and Phi-3.5-MoE-instruct is developed by Microsoft.

Related comparisons