Compare

Mistral X-Large vs Llama 4 Scout

Mistral vs Meta. Specs, benchmarks, and real per-task cost — all in one page.

Verdict

Mistral X-Large leads on LMSYS ELO (1318 vs 1265). Llama 4 Scout is ~6.5× cheaper on a 3:1 input:output blend.

Mistral

European frontier model. EU-hosted inference, strong European language coverage, Apache-licensed weights.

EU data residencyMultilingual strengthOpen license

Meta

The 70B workhorse open-weight. Fits on a single H100, beloved by self-hosters.

Single-GPU deployableDirt cheap on aggregatorsStrong fine-tuning base

Pricing

Input / 1M$2.00$0.35

Output / 1M$6.00$0.80

Context256K128K

Max output16K8K

LicenseOpen weightsOpen weights

Released2026-01-282025-12-10

Benchmarks

LMSYS ELO1318.01265.0

MMLU Pro83.577.2

HumanEval88.082.4

MATH78.272.5

IFEval86.584.1

Per-task cost

Summarize a 1-hour meeting transcript$0.033$0.0057

Review a 500-line pull request$0.028$0.0044

Answer a customer support ticket$0.011$0.0017

Extract structured data from a resume$0.016$0.0026

Debug a stack trace with context$0.024$0.0037

Per-call cost using published token counts for each task. Real-world prompts vary.

Add up to four models, tweak tasks live.