Compare

GPT-5 Mini vs o4

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

Verdict

GPT-5 Mini is ~30.0× cheaper on a 3:1 input:output blend.

OpenAI

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

Very low latencyCheap enough for mass consumer apps

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$0.50$15.00

Output / 1M$2.00$60.00

Context256K200K

Max output16K100K

LicenseProprietaryProprietary

Released2026-01-212026-02-18

Benchmarks

LMSYS ELO1288.0—

MMLU Pro78.593.8

HumanEval85.592.3

SWE-Bench—68.0

MATH79.896.2

GPQA—82.5

IFEval85.4—

Per-task cost

Summarize a 1-hour meeting transcript$0.0085$0.255

Review a 500-line pull request$0.0080$0.240

Answer a customer support ticket$0.0031$0.093

Extract structured data from a resume$0.0045$0.135

Debug a stack trace with context$0.0070$0.210

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

Add up to four models, tweak tasks live.