Compare

GPT-5 Mini vs Gemini 2.5 Flash

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

Verdict

Gemini 2.5 Flash leads on LMSYS ELO (1312 vs 1288). Gemini 2.5 Flash is ~1.7× 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

Google’s price/performance darling. 1M context at $0.30/M input — nobody comes close on throughput-per-dollar.

Absurd cost-to-context ratioFast multimodalFree tier via AI Studio

Pricing

Input / 1M$0.50$0.30

Output / 1M$2.00$1.20

Context256K1.0M

Max output16K32K

LicenseProprietaryProprietary

Released2026-01-212026-02-05

Benchmarks

LMSYS ELO1288.01312.0

MMLU Pro78.582.1

HumanEval85.585.8

MATH79.884.2

MMMU—74.6

IFEval85.486.1

Per-task cost

Summarize a 1-hour meeting transcript$0.0085$0.0051

Review a 500-line pull request$0.0080$0.0048

Answer a customer support ticket$0.0031$0.0019

Extract structured data from a resume$0.0045$0.0027

Debug a stack trace with context$0.0070$0.0042

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

Add up to four models, tweak tasks live.