Compare

Mistral X-Large vs o4

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

Verdict

Mistral X-Large is ~8.8× cheaper on a 3:1 input:output blend. Mistral X-Large is open-weights, the other is proprietary.

Mistral

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

EU data residencyMultilingual strengthOpen license

OpenAI

Deep-reasoning model. Spends more tokens thinking to crush math, science, and hard coding problems.

State-of-the-art math and scienceExtremely high-ceiling reasoning

Pricing

Input / 1M$2.00$15.00

Output / 1M$6.00$60.00

Context256K200K

Max output16K100K

LicenseOpen weightsProprietary

Released2026-01-282026-02-18

Benchmarks

LMSYS ELO1318.0—

MMLU Pro83.593.8

HumanEval88.092.3

SWE-Bench—68.0

MATH78.296.2

GPQA—82.5

IFEval86.5—

Per-task cost

Summarize a 1-hour meeting transcript$0.033$0.255

Review a 500-line pull request$0.028$0.240

Answer a customer support ticket$0.011$0.093

Extract structured data from a resume$0.016$0.135

Debug a stack trace with context$0.024$0.210

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

Add up to four models, tweak tasks live.