The AI arena is free today

Open Superagent

Mistral Small 3.1 24B Instruct vs Nova Lite

Mistral Small 3.1 24B Instruct and Nova Lite are closely matched at 4.2 and 7.6 on the LLM Stats Score.

Mistral AI · Amazon · Updated for 2026

Which is better?

Mistral Small 3.1 24B Instruct and Nova Lite are closely matched on the overall LLM Stats Score at 4.2 and 7.6.

In the 5 individual benchmarks reported for both models, Mistral Small 3.1 24B Instruct wins 4; 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 Mistral Small 3.1 24B Instruct

  • you value its reported benchmark strengths — it wins 4 of 5 exact shared results
  • you want the most recent training data — it shipped Mar 2025
  • you need open weights you can self-host or fine-tune

Choose Nova Lite

  • you want predictable pricing at $0.06/M input and $0.24/M output

At a glance

The differences that matter most.

Mistral Small 3.1 24B Instruct
Mistral AI
Nova Lite
Amazon
Core performance indexes
LLM Stats Score
4.2
#302
7.6
#287
Reasoning
4.2
#296
7.1
#284
Coding
9.7
#170
5.6
#197
Cost, coverage & limits
Benchmark wins
4 of 5
1 of 5
Input price
— / M
$0.06 / M
Output price
— / M
$0.24 / M
Context window
—
300,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Mistral Small 3.1 24B Instruct
Nova Lite
Math
7.9#261
13.6#227
Finance
7.3#160
8.8#154
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

9 reported for Mistral Small 3.1 24B Instruct · 27 for Nova Lite

5 shared

Mistral Small 3.1 24B Instruct outperforms in 4 benchmarks (GPQA, HumanEval, MMLU, MMMU), while Nova Lite is better at 1 benchmark (MATH).

Mistral Small 3.1 24B Instruct significantly outperforms across most benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Nova Lite specifies input context (300,000 tokens). Only Nova Lite specifies output context (2,048 tokens).

Mistral AI
Mistral Small 3.1 24B Instruct
Input- tokens
Output- tokens
Amazon
Nova Lite
Input300,000 tokens
Output2,048 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Mistral Small 3.1 24B Instruct and Nova Lite support multimodal inputs.

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

Mistral Small 3.1 24B Instruct

Text
Images
Audio
Video

Nova Lite

Text
Images
Audio
Video

License

Usage and distribution terms

Mistral Small 3.1 24B Instruct is licensed under Apache 2.0, while Nova Lite uses a proprietary license.

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

Mistral Small 3.1 24B Instruct

Apache 2.0

Open weights

Nova Lite

Proprietary

Closed source

Release Timeline

When each model was launched

Mistral Small 3.1 24B Instruct was released on 2025-03-17, while Nova Lite was released on 2024-11-20.

Mistral Small 3.1 24B Instruct is 4 months newer than Nova Lite.

Mistral Small 3.1 24B Instruct

Mar 17, 2025

1.5 years ago

3mo newer
Nova Lite

Nov 20, 2024

1.8 years 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?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Mistral Small 3.1 24B Instruct and Nova Lite side-by-side, then vote on the output you prefer.

Mistral Small 3.1 24B Instruct
✓ Preferred
Nova Lite
Open in Playground

FAQ

Common questions about Mistral Small 3.1 24B Instruct vs Nova Lite.

Which is better, Mistral Small 3.1 24B Instruct or Nova Lite?

Mistral Small 3.1 24B Instruct and Nova Lite are closely matched on the LLM Stats Score at 4.2 and 7.6. Mistral Small 3.1 24B Instruct is made by Mistral AI and Nova Lite 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 Small 3.1 24B Instruct compare to Nova Lite in benchmarks?

Mistral Small 3.1 24B Instruct scores HumanEval: 88.4%, MMLU: 80.6%, TriviaQA: 80.5%, MBPP: 74.7%, MATH: 69.3%. Nova Lite scores GSM8k: 94.5%, ARC-C: 92.4%, DocVQA: 92.4%, IFEval: 89.7%, Translation en→Set1 COMET22: 88.8%.

What are the context window sizes for Mistral Small 3.1 24B Instruct and Nova Lite?

Mistral Small 3.1 24B Instruct supports an unknown number of tokens and Nova Lite supports 300K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Mistral Small 3.1 24B Instruct and Nova Lite?

Key differences include LLM Stats Score (4.2 vs 7.6), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Mistral Small 3.1 24B Instruct and Nova Lite?

Mistral Small 3.1 24B Instruct is developed by Mistral AI and Nova Lite is developed by Amazon.

Related comparisons