The AI arena is free today

Open Superagent

Codestral-22B vs Llama 3.1 70B Instruct

Codestral-22B and Llama 3.1 70B Instruct are closely matched at 0.1 and 7.7 on the LLM Stats Score.

Mistral AI · Meta · Updated for 2026

Which is better?

Codestral-22B and Llama 3.1 70B Instruct are closely matched on the overall LLM Stats Score at 0.1 and 7.7.

In the 1 individual benchmarks reported for both models, Codestral-22B wins 1; this is a narrower head-to-head signal than the composite indexes.

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

Choose Codestral-22B

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results

Choose Llama 3.1 70B Instruct

  • you want the most recent training data — it shipped Jul 2024

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Llama 3.1 70B Instruct
Meta
Core performance indexes
LLM Stats Score
0.1
#324
7.7
#284
Reasoning
-0.1
#316
6.4
#286
Coding
2.5
#223
3.6
#213
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
— / M
$0.20 / M
Output price
— / M
$0.20 / M
Context window
—
128,000

Individual benchmarks

7 reported for Codestral-22B · 18 for Llama 3.1 70B Instruct

1 shared

Codestral-22B outperforms in 1 benchmarks (HumanEval), while Llama 3.1 70B Instruct is better at 0 benchmarks.

Codestral-22B significantly outperforms across most benchmarks.

Thu Sep 10 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

47.8B diff

Llama 3.1 70B Instruct has 47.8B more parameters than Codestral-22B, making it 215.3% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Meta
Llama 3.1 70B Instruct
70.0Bparameters
22.2B
Codestral-22B
70.0B
Llama 3.1 70B Instruct

Context Window

Maximum input and output token capacity

Only Llama 3.1 70B Instruct specifies input context (128,000 tokens). Only Llama 3.1 70B Instruct specifies output context (128,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Meta
Llama 3.1 70B Instruct
Input128,000 tokens
Output128,000 tokens
Thu Sep 10 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Llama 3.1 70B Instruct uses Llama 3.1 Community License.

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

Codestral-22B

MNPL-0.1

Open weights

Llama 3.1 70B Instruct

Llama 3.1 Community License

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Llama 3.1 70B Instruct was released on 2024-07-23.

Llama 3.1 70B Instruct is 2 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Llama 3.1 70B Instruct

Jul 23, 2024

2.1 years ago

1mo 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→

Judge for yourself.

Run your own prompts against Codestral-22B and Llama 3.1 70B Instruct side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Llama 3.1 70B Instruct
Open in Playground

FAQ

Common questions about Codestral-22B vs Llama 3.1 70B Instruct.

Which is better, Codestral-22B or Llama 3.1 70B Instruct?

Codestral-22B and Llama 3.1 70B Instruct are closely matched on the LLM Stats Score at 0.1 and 7.7. Codestral-22B is made by Mistral AI and Llama 3.1 70B Instruct is made by Meta. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Llama 3.1 70B Instruct in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Llama 3.1 70B Instruct scores GSM-8K (CoT): 95.1%, ARC-C: 94.8%, API-Bank: 90.0%, IFEval: 87.5%, Multilingual MGSM (CoT): 86.9%.

What are the context window sizes for Codestral-22B and Llama 3.1 70B Instruct?

Codestral-22B supports an unknown number of tokens and Llama 3.1 70B Instruct supports 128K 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 Llama 3.1 70B Instruct?

Key differences include LLM Stats Score (0.1 vs 7.7), licensing (MNPL-0.1 vs Llama 3.1 Community License). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Llama 3.1 70B Instruct?

Codestral-22B is developed by Mistral AI and Llama 3.1 70B Instruct is developed by Meta.

Related comparisons