Compare

GPT-5 Mini vs Gemini 2.5 Ultra

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

Verdict

Gemini 2.5 Ultra leads on LMSYS ELO (1385 vs 1288). GPT-5 Mini is ~12.0× 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

Google DeepMind

2M-token context, native video understanding, and Google’s deepest multimodal stack. The long-context king.

2M context windowNative videoBest multimodal reasoning

Pricing

Input / 1M$0.50$7.00

Output / 1M$2.00$21.00

Context256K2.0M

Max output16K64K

LicenseProprietaryProprietary

Released2026-01-212026-02-05

Benchmarks

LMSYS ELO1288.01385.0

MMLU Pro78.590.4

HumanEval85.590.2

SWE-Bench—58.3

MATH79.892.0

MMMU—82.1

IFEval85.489.7

Per-task cost

Summarize a 1-hour meeting transcript$0.0085$0.115

Review a 500-line pull request$0.0080$0.098

Answer a customer support ticket$0.0031$0.038

Extract structured data from a resume$0.0045$0.056

Debug a stack trace with context$0.0070$0.084

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

Add up to four models, tweak tasks live.