The AI arena is free today

Open Superagent

Llama 4 Scout vs Mistral Large 3 (675B Base)

Llama 4 Scout and Mistral Large 3 (675B Base) are closely matched at 7.8 and 8.8 on the LLM Stats Score.

Meta · Mistral AI · Updated for 2026

Which is better?

Llama 4 Scout and Mistral Large 3 (675B Base) are closely matched on the overall LLM Stats Score at 7.8 and 8.8.

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 Llama 4 Scout

  • you want predictable pricing at $0.08/M input and $0.30/M output

Choose Mistral Large 3 (675B Base)

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

At a glance

The differences that matter most.

Llama 4 Scout
Meta
Mistral Large 3 (675B Base)
Mistral AI
Core performance indexes
LLM Stats Score
7.8
#299
8.8
#291
Reasoning
6.6
#302
9.0
#284
Coding
0.3
#255
1.2
#247
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
$0.08 / M
— / M
Output price
$0.30 / M
— / M
Context window
10,000,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Llama 4 Scout
Mistral Large 3 (675B Base)
Math
12.8#238
18.8#183
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for Llama 4 Scout · 5 for Mistral Large 3 (675B Base)

2 shared

Llama 4 Scout outperforms in 1 benchmarks (GPQA), while Mistral Large 3 (675B Base) is better at 1 benchmark (LiveCodeBench).

Both models are evenly matched across the benchmarks.

Thu Oct 08 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

566.0B diff

Mistral Large 3 (675B Base) has 566.0B more parameters than Llama 4 Scout, making it 519.3% larger.

Meta
Llama 4 Scout
109.0Bparameters
Mistral AI
Mistral Large 3 (675B Base)
675.0Bparameters
109.0B
Llama 4 Scout
675.0B
Mistral Large 3 (675B Base)

Context Window

Maximum input and output token capacity

Only Llama 4 Scout specifies input context (10,000,000 tokens). Only Llama 4 Scout specifies output context (10,000,000 tokens).

Meta
Llama 4 Scout
Input10,000,000 tokens
Output10,000,000 tokens
Mistral AI
Mistral Large 3 (675B Base)
Input- tokens
Output- tokens
Thu Oct 08 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Llama 4 Scout and Mistral Large 3 (675B Base) support multimodal inputs.

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

Llama 4 Scout

Text
Images
Audio
Video

Mistral Large 3 (675B Base)

Text
Images
Audio
Video

License

Usage and distribution terms

Llama 4 Scout is licensed under Llama 4 Community License Agreement, while Mistral Large 3 (675B Base) uses Apache 2.0.

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

Llama 4 Scout

Llama 4 Community License Agreement

Open weights

Mistral Large 3 (675B Base)

Apache 2.0

Open weights

Release Timeline

When each model was launched

Llama 4 Scout was released on 2025-04-05, while Mistral Large 3 (675B Base) was released on 2025-12-04.

Mistral Large 3 (675B Base) is 8 months newer than Llama 4 Scout.

Llama 4 Scout

Apr 5, 2025

1.5 years ago

Mistral Large 3 (675B Base)

Dec 4, 2025

10 months ago

8mo 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?

Judge for yourself.

Run your own prompts against Llama 4 Scout and Mistral Large 3 (675B Base) side-by-side, then vote on the output you prefer.

Llama 4 Scout
✓ Preferred
Mistral Large 3 (675B Base)
Open in Playground

FAQ

Common questions about Llama 4 Scout vs Mistral Large 3 (675B Base).

Which is better, Llama 4 Scout or Mistral Large 3 (675B Base)?

Llama 4 Scout and Mistral Large 3 (675B Base) are closely matched on the LLM Stats Score at 7.8 and 8.8. Llama 4 Scout is made by Meta and Mistral Large 3 (675B Base) 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 Llama 4 Scout compare to Mistral Large 3 (675B Base) in benchmarks?

Llama 4 Scout scores DocVQA: 94.4%, MGSM: 90.6%, ChartQA: 88.8%, MMLU: 79.6%, MMLU-Pro: 74.3%. Mistral Large 3 (675B Base) scores MMMLU: 85.5%, AMC_2022_23: 52.0%, GPQA: 43.9%, LiveCodeBench: 34.4%, SimpleQA: 23.8%.

What are the context window sizes for Llama 4 Scout and Mistral Large 3 (675B Base)?

Llama 4 Scout supports 10.0M tokens and Mistral Large 3 (675B Base) 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 Llama 4 Scout and Mistral Large 3 (675B Base)?

Key differences include LLM Stats Score (7.8 vs 8.8), licensing (Llama 4 Community License Agreement vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Llama 4 Scout and Mistral Large 3 (675B Base)?

Llama 4 Scout is developed by Meta and Mistral Large 3 (675B Base) is developed by Mistral AI.

Related comparisons