Compare

Mistral X-Large vs GPT-5 Mini

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

Verdict

Mistral X-Large leads on LMSYS ELO (1318 vs 1288). GPT-5 Mini is ~3.4× cheaper on a 3:1 input:output blend. Mistral X-Large is open-weights, the other is proprietary.

Mistral

Mistral X-Large

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

EU data residencyMultilingual strengthOpen license

OpenAI

GPT-5 Mini

GPT-5’s smaller, cheaper sibling. Optimized for chat and lightweight agent tasks.

Very low latencyCheap enough for mass consumer apps

Pricing

Input / 1M$2.00$0.50

Output / 1M$6.00$2.00

Context256K256K

Max output16K16K

LicenseOpen weightsProprietary

Released2026-01-282026-01-21

Benchmarks

LMSYS ELO1318.01288.0

MMLU Pro83.578.5

HumanEval88.085.5

MATH78.279.8

IFEval86.585.4

Per-task cost

Summarize a 1-hour meeting transcript$0.033$0.0085

Review a 500-line pull request$0.028$0.0080

Answer a customer support ticket$0.011$0.0031

Extract structured data from a resume$0.016$0.0045

Debug a stack trace with context$0.024$0.0070

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

Tool

Interactive compare →

Add up to four models, tweak tasks live.