Compare

o4 vs GPT-5 Mini

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

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

OpenAI

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

Very low latencyCheap enough for mass consumer apps

Pricing

Input / 1M$15.00$0.50

Output / 1M$60.00$2.00

Context200K256K

Max output100K16K

LicenseProprietaryProprietary

Released2026-02-182026-01-21

Benchmarks

LMSYS ELO—1288.0

MMLU Pro93.878.5

HumanEval92.385.5

SWE-Bench68.0—

MATH96.279.8

GPQA82.5—

IFEval—85.4

Per-task cost

Summarize a 1-hour meeting transcript$0.255$0.0085

Review a 500-line pull request$0.240$0.0080

Answer a customer support ticket$0.093$0.0031

Extract structured data from a resume$0.135$0.0045

Debug a stack trace with context$0.210$0.0070

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

Add up to four models, tweak tasks live.