ModelCompare
Compare

Model vs model

Llama 4 Scout vs Mistral Small 4

Mistral Small 4 has the biggest gap on long documents, scoring 49.7 against 27.7 on AA-LCR, and it also leads on the Intelligence Index, 11.3 to 6.5. It is cheaper too, at $0.26 per 1M tokens blended against $0.29. Pick Mistral Small 4 for long documents, PDFs and reasoning. Pick Llama 4 Scout for text and image work if you want Meta's model.

By ModelCompare ·

Free to try, no account needed. You see each answer’s cost and speed.

At a glance

Longer bar means the bigger number.

Blended price · per 1M tokens, lower is better

Llama 4 Scout$0.29
Mistral Small 4$0.26

Intelligence Index · Artificial Analysis, higher is better

Llama 4 Scout6.5
Mistral Small 411.3

Context window · tokens it can read at once

Llama 4 Scout128K
Mistral Small 4262K

Where they sit among all 44 models

Llama 4 Scout ranks 43rd of the 43 models with an Intelligence Index, Mistral Small 4 39th. Up and to the left is smarter for less money. Hover or tap a dot for its numbers, then click it to compare that model with Llama 4 Scout.

Intelligence: the Artificial Analysis Intelligence Index. Price: blended per 1M tokens, 3 parts input to 1 part output, on a log scale.

Which one to pick

Pick Mistral Small 4 if

  • you want the lower bill ($0.26 vs $0.29 per 1M tokens blended)
  • you want the higher overall score (11.3 vs 6.5)
  • you care about AA-LCR (long documents): 49.7 vs 27.7
  • you care about coding: 26.6 vs 8.2

See how they answer your prompt

How smart is each one?

Of the 15 scores both models have, Mistral Small 4 is ahead on 13, and 2 are within a point.

Every intelligence score we have

Out of 100, higher is better. Llama 4 Scout Mistral Small 4

Overall

  • Intelligence Index

By area

  • Coding

  • Math

    Mistral Small 4: not scored yet

  • Agentic work

By field of work

  • Finance & accounting

  • Legal

  • Healthcare & medicine

    Llama 4 Scout: not scored yet

  • Economics

  • Engineering

  • Strategy & operations

Benchmarks

  • Hard reasoning · Humanity's Last Exam

  • Science · GPQA Diamond

  • Knowledge · MMLU-Pro

    Mistral Small 4: not scored yet

  • Competitive coding · LiveCodeBench

    Mistral Small 4: not scored yet

  • Scientific coding · SciCode

  • Terminal tasks · Terminal-Bench 4.0

  • Tool use · τ-Bench Banking

  • Instruction following · IFBench

  • Long documents · AA-LCR

  • Competition math · AIME 2025

    Mistral Small 4: not scored yet

  • Competition math · AIME 2024

    Mistral Small 4: not scored yet

  • Math · MATH-500

    Mistral Small 4: not scored yet

  • Uncensored · UGI

    Llama 4 Scout: not scored yet

Test them on your own question

The specs

Spec Llama 4 Scout Mistral Small 4
Input price$0.17 per 1M$0.15 per 1M
Output price$0.66 per 1M$0.60 per 1M
Cost per test taskNot tested$0.0150
Context window128K262K
Max output8K256K
AcceptsText, ImageText, Image, PDF
Open weightsYesYes
LabMetaMistral AI
ReleasedApr 2025Mar 2026
Knowledge cutoffAug 2024Jun 2025

Blended price weighs 3 parts input to 1 part output. List prices from models.dev. Cost per test task from Artificial Analysis.

Questions

Is Llama 4 Scout or Mistral Small 4 cheaper?

Mistral Small 4 is cheaper. It charges $0.15 per 1M input tokens and $0.60 per 1M output tokens, against $0.17 and $0.66 for Llama 4 Scout. Blended 3 parts input to 1 part output, that is $0.26 against $0.29 per 1M tokens.

Which is smarter, Llama 4 Scout or Mistral Small 4?

Mistral Small 4 scores higher on the Artificial Analysis Intelligence Index, 11.3 against 6.5 for Llama 4 Scout. The biggest differences are on AA-LCR (27.7 vs 49.7) and Coding (8.2 vs 26.6).

Which has the longer context window?

Mistral Small 4 accepts 262K tokens, against 128K for Llama 4 Scout.

Can I compare Llama 4 Scout and Mistral Small 4 on my own prompt?

Yes. ModelCompare sends one prompt to both models at once and shows each answer side by side with what it cost. You can try it free without an account.

Still deciding? Send one prompt to both and read the answers side by side, with what each one cost. Compare Llama 4 Scout and Mistral Small 4 →

Where the numbers come from

Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except SimpleQA, which is from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard. The hallucination test is ours: questions with one exact answer, fake evidence pushed against right answers and requests that tempt a model to name packages that don’t exist. Prices are list prices from models.dev. Example answers come from our own test runs. Updated October 25, 2026.