The AI arena is free today

Open Superagent

Mistral Medium 3.5 vs Nova 2 Omni

Mistral Medium 3.5 and Nova 2 Omni are closely matched at 26.9 and 25.7 on the LLM Stats Score.

Mistral AI · Amazon · Updated for 2026

Which is better?

Mistral Medium 3.5 and Nova 2 Omni are closely matched on the overall LLM Stats Score at 26.9 and 25.7.

The models split the 2 individual benchmarks reported for both models evenly.

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

Choose Mistral Medium 3.5

  • you want the most recent training data — it shipped Apr 2026
  • you need open weights you can self-host or fine-tune

Choose Nova 2 Omni

  • you are already invested in the Amazon ecosystem

At a glance

The differences that matter most.

Mistral Medium 3.5
Mistral AI
Nova 2 Omni
Amazon
Core performance indexes
LLM Stats Score
26.9
#153
25.7
#164
Reasoning
27.2
#145
28.0
#139
Agents
8.9
#138
4.6
#159
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
$1.50 / M
— / M
Output price
$7.50 / M
— / M
Context window
256,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Mistral Medium 3.5
Nova 2 Omni
Math
18.9#173
25.1#116
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for Mistral Medium 3.5 · 18 for Nova 2 Omni

2 shared

Mistral Medium 3.5 outperforms in 1 benchmarks (IFBench), while Nova 2 Omni is better at 1 benchmark (AIME 2025).

Both models are evenly matched across the benchmarks.

Fri Oct 02 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Mistral Medium 3.5 specifies input context (256,000 tokens). Only Mistral Medium 3.5 specifies output context (256,000 tokens).

Mistral AI
Mistral Medium 3.5
Input256,000 tokens
Output256,000 tokens
Amazon
Nova 2 Omni
Input- tokens
Output- tokens
Fri Oct 02 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Mistral Medium 3.5 and Nova 2 Omni support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Mistral Medium 3.5

Text
Images
Audio
Video

Nova 2 Omni

Text
Images
Audio
Video

License

Usage and distribution terms

Mistral Medium 3.5 is licensed under Modified MIT License, while Nova 2 Omni uses a proprietary license.

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

Mistral Medium 3.5

Modified MIT License

Open weights

Nova 2 Omni

Proprietary

Closed source

Release Timeline

When each model was launched

Mistral Medium 3.5 was released on 2026-04-29, while Nova 2 Omni was released on 2025-12-02.

Mistral Medium 3.5 is 5 months newer than Nova 2 Omni.

Mistral Medium 3.5

Apr 29, 2026

5 months ago

4mo newer
Nova 2 Omni

Dec 2, 2025

10 months ago

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 Mistral Medium 3.5 and Nova 2 Omni side-by-side, then vote on the output you prefer.

Mistral Medium 3.5
✓ Preferred
Nova 2 Omni
Open in Playground

FAQ

Common questions about Mistral Medium 3.5 vs Nova 2 Omni.

Which is better, Mistral Medium 3.5 or Nova 2 Omni?

Mistral Medium 3.5 and Nova 2 Omni are closely matched on the LLM Stats Score at 26.9 and 25.7. Mistral Medium 3.5 is made by Mistral AI and Nova 2 Omni is made by Amazon. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Mistral Medium 3.5 compare to Nova 2 Omni in benchmarks?

Mistral Medium 3.5 scores COLLIE: 95.8%, Tau3 Telecom: 91.4%, AIME 2025: 86.3%, SWE-Bench Verified: 77.6%, Tau3 Retail: 76.1%. Nova 2 Omni scores AIME 2025: 92.1%, RefCOCOg: 86.3%, ScreenSpot: 85.4%, MMLU-Pro: 80.7%, Tau2 Telecom: 80.0%.

What are the context window sizes for Mistral Medium 3.5 and Nova 2 Omni?

Mistral Medium 3.5 supports 256K tokens and Nova 2 Omni supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Mistral Medium 3.5 and Nova 2 Omni?

Key differences include LLM Stats Score (26.9 vs 25.7), licensing (Modified MIT License vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Mistral Medium 3.5 and Nova 2 Omni?

Mistral Medium 3.5 is developed by Mistral AI and Nova 2 Omni is developed by Amazon.

Related comparisons