The AI arena is free today

Open Superagent

Mistral Large 3 (675B Base) vs Mistral Small 3 24B Instruct

Mistral Large 3 (675B Base) and Mistral Small 3 24B Instruct are closely matched at 8.8 and 4.2 on the LLM Stats Score.

Mistral AI · Mistral AI · Updated for 2026

Which is better?

Mistral Large 3 (675B Base) and Mistral Small 3 24B Instruct are closely matched on the overall LLM Stats Score at 8.8 and 4.2.

In the 1 individual benchmarks reported for both models, Mistral Small 3 24B Instruct 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 Mistral Large 3 (675B Base)

  • you want the most recent training data — it shipped Dec 2025

Choose Mistral Small 3 24B Instruct

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

At a glance

The differences that matter most.

Mistral Large 3 (675B Base)
Mistral AI
Mistral Small 3 24B Instruct
Mistral AI
Core performance indexes
LLM Stats Score
8.8
#291
4.2
#319
Reasoning
9.0
#284
3.7
#315
Coding
1.2
#247
4.6
#219
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$0.05 / M
Output price
— / M
$0.08 / M
Context window
—
32,768

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Mistral Large 3 (675B Base)
Mistral Small 3 24B Instruct
Math
18.8#183
6.9#273
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

5 reported for Mistral Large 3 (675B Base) · 8 for Mistral Small 3 24B Instruct

1 shared

Mistral Large 3 (675B Base) outperforms in 0 benchmarks, while Mistral Small 3 24B Instruct is better at 1 benchmark (GPQA).

Mistral Small 3 24B Instruct significantly outperforms across most benchmarks.

Thu Oct 08 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

651.0B diff

Mistral Large 3 (675B Base) has 651.0B more parameters than Mistral Small 3 24B Instruct, making it 2712.5% larger.

Mistral AI
Mistral Large 3 (675B Base)
675.0Bparameters
Mistral AI
Mistral Small 3 24B Instruct
24.0Bparameters
675.0B
Mistral Large 3 (675B Base)
24.0B
Mistral Small 3 24B Instruct

Context Window

Maximum input and output token capacity

Only Mistral Small 3 24B Instruct specifies input context (32,768 tokens). Only Mistral Small 3 24B Instruct specifies output context (32,768 tokens).

Mistral AI
Mistral Large 3 (675B Base)
Input- tokens
Output- tokens
Mistral AI
Mistral Small 3 24B Instruct
Input32,768 tokens
Output32,768 tokens
Thu Oct 08 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Mistral Large 3 (675B Base) supports multimodal inputs, whereas Mistral Small 3 24B Instruct does not.

Mistral Large 3 (675B Base) can handle both text and other forms of data like images, making it suitable for multimodal applications.

Mistral Large 3 (675B Base)

Text
Images
Audio
Video

Mistral Small 3 24B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Mistral Large 3 (675B Base)

Apache 2.0

Open weights

Mistral Small 3 24B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Mistral Large 3 (675B Base) was released on 2025-12-04, while Mistral Small 3 24B Instruct was released on 2025-01-30.

Mistral Large 3 (675B Base) is 10 months newer than Mistral Small 3 24B Instruct.

Mistral Large 3 (675B Base)

Dec 4, 2025

10 months ago

10mo newer
Mistral Small 3 24B Instruct

Jan 30, 2025

1.7 years ago

Knowledge Cutoff

When training data ends

Mistral Small 3 24B Instruct has a documented knowledge cutoff of 2023-10-01, while Mistral Large 3 (675B Base)'s cutoff date is not specified.

We can confirm Mistral Small 3 24B Instruct's training data extends to 2023-10-01, but cannot make a direct comparison without Mistral Large 3 (675B Base)'s cutoff date.

Mistral Large 3 (675B Base)

—

Mistral Small 3 24B Instruct

Oct 2023

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Mistral Large 3 (675B Base) and Mistral Small 3 24B Instruct side-by-side, then vote on the output you prefer.

Mistral Large 3 (675B Base)
✓ Preferred
Mistral Small 3 24B Instruct
Open in Playground

FAQ

Common questions about Mistral Large 3 (675B Base) vs Mistral Small 3 24B Instruct.

Which is better, Mistral Large 3 (675B Base) or Mistral Small 3 24B Instruct?

Mistral Large 3 (675B Base) and Mistral Small 3 24B Instruct are closely matched on the LLM Stats Score at 8.8 and 4.2. Mistral Large 3 (675B Base) is made by Mistral AI and Mistral Small 3 24B Instruct is made by Mistral AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Mistral Large 3 (675B Base) compare to Mistral Small 3 24B Instruct in benchmarks?

Mistral Large 3 (675B Base) scores MMMLU: 85.5%, AMC_2022_23: 52.0%, GPQA: 43.9%, LiveCodeBench: 34.4%, SimpleQA: 23.8%. Mistral Small 3 24B Instruct scores Arena Hard: 87.6%, HumanEval: 84.8%, MT-Bench: 83.5%, IFEval: 82.9%, MATH: 70.6%.

What are the context window sizes for Mistral Large 3 (675B Base) and Mistral Small 3 24B Instruct?

Mistral Large 3 (675B Base) supports an unknown number of tokens and Mistral Small 3 24B Instruct supports 33K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Mistral Large 3 (675B Base) and Mistral Small 3 24B Instruct?

Key differences include LLM Stats Score (8.8 vs 4.2), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.

Related comparisons