Compare

GPT-5 Turbo vs GPT-5 Mini

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

Verdict

GPT-5 Turbo leads on LMSYS ELO (1398 vs 1288). GPT-5 Mini is ~12.0× cheaper on a 3:1 input:output blend.

OpenAI

OpenAI’s flagship unified model. Handles text, vision, and audio natively. The generalist benchmark champion.

Native multimodalStrong math and scienceHuge ecosystem

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$6.00$0.50

Output / 1M$24.00$2.00

Context400K256K

Max output32K16K

LicenseProprietaryProprietary

Released2026-01-212026-01-21

Benchmarks

LMSYS ELO1398.01288.0

MMLU Pro91.278.5

HumanEval93.085.5

SWE-Bench65.8—

MATH91.579.8

GPQA68.1—

MMMU78.8—

IFEval88.985.4

Per-task cost

Summarize a 1-hour meeting transcript$0.102$0.0085

Review a 500-line pull request$0.096$0.0080

Answer a customer support ticket$0.037$0.0031

Extract structured data from a resume$0.054$0.0045

Debug a stack trace with context$0.084$0.0070

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

Add up to four models, tweak tasks live.