The AI arena is free today

Open Superagent

Codestral-22B vs Llama-3.3 Nemotron Super 49B v1

Llama-3.3 Nemotron Super 49B v1 leads the LLM Stats Score 13.1 to 0.0.

Mistral AI · NVIDIA · Updated for 2026

Which is better?

Llama-3.3 Nemotron Super 49B v1 leads the overall LLM Stats Score 13.1 to 0.0, ranking #252 overall.

In the 1 individual benchmarks reported for both models, Llama-3.3 Nemotron Super 49B v1 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 are already invested in the Mistral AI ecosystem

Choose Llama-3.3 Nemotron Super 49B v1

  • overall performance matters — it scores 13.1 and ranks #252 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Mar 2025

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Llama-3.3 Nemotron Super 49B v1
NVIDIA
Core performance indexes
LLM Stats Score
0.0
#332
13.1
#252
Reasoning
-0.1
#324
13.2
#245
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—

Individual benchmarks

7 reported for Codestral-22B · 7 for Llama-3.3 Nemotron Super 49B v1

1 shared

Codestral-22B outperforms in 0 benchmarks, while Llama-3.3 Nemotron Super 49B v1 is better at 1 benchmark (MBPP).

Llama-3.3 Nemotron Super 49B v1 significantly outperforms across most benchmarks.

Sun Sep 27 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

27.7B diff

Llama-3.3 Nemotron Super 49B v1 has 27.7B more parameters than Codestral-22B, making it 124.8% larger.

Mistral AI
Codestral-22B
22.2Bparameters
NVIDIA
Llama-3.3 Nemotron Super 49B v1
49.9Bparameters
22.2B
Codestral-22B
49.9B
Llama-3.3 Nemotron Super 49B v1

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Llama-3.3 Nemotron Super 49B v1 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-3.3 Nemotron Super 49B v1

Llama 3.1 Community License

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Llama-3.3 Nemotron Super 49B v1 was released on 2025-03-18.

Llama-3.3 Nemotron Super 49B v1 is 10 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Llama-3.3 Nemotron Super 49B v1

Mar 18, 2025

1.5 years ago

9mo newer

Knowledge Cutoff

When training data ends

Llama-3.3 Nemotron Super 49B v1 has a documented knowledge cutoff of 2023-12-31, while Codestral-22B's cutoff date is not specified.

We can confirm Llama-3.3 Nemotron Super 49B v1's training data extends to 2023-12-31, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

Llama-3.3 Nemotron Super 49B v1

Dec 2023

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and Llama-3.3 Nemotron Super 49B v1 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Llama-3.3 Nemotron Super 49B v1
Open in Playground

FAQ

Common questions about Codestral-22B vs Llama-3.3 Nemotron Super 49B v1.

Which is better, Codestral-22B or Llama-3.3 Nemotron Super 49B v1?

Llama-3.3 Nemotron Super 49B v1 leads the LLM Stats Score 13.1 to 0.0. Codestral-22B is made by Mistral AI and Llama-3.3 Nemotron Super 49B v1 is made by NVIDIA. 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-3.3 Nemotron Super 49B v1 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Llama-3.3 Nemotron Super 49B v1 scores MATH-500: 96.6%, MT-Bench: 91.7%, MBPP: 91.3%, Arena Hard: 88.3%, BFCL v2: 73.7%.

What are the main differences between Codestral-22B and Llama-3.3 Nemotron Super 49B v1?

Key differences include LLM Stats Score (0.0 vs 13.1), 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-3.3 Nemotron Super 49B v1?

Codestral-22B is developed by Mistral AI and Llama-3.3 Nemotron Super 49B v1 is developed by NVIDIA.

Related comparisons