Compare

Gemini 2.5 Ultra vs Gemini 2.5 Flash

Google DeepMind 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 1312). Gemini 2.5 Flash is ~20.0× cheaper on a 3:1 input:output blend.

Google DeepMind

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

2M context windowNative videoBest multimodal reasoning

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$7.00$0.30

Output / 1M$21.00$1.20

Context2.0M1.0M

Max output64K32K

LicenseProprietaryProprietary

Released2026-02-052026-02-05

Benchmarks

LMSYS ELO1385.01312.0

MMLU Pro90.482.1

HumanEval90.285.8

SWE-Bench58.3—

MATH92.084.2

MMMU82.174.6

IFEval89.786.1

Per-task cost

Summarize a 1-hour meeting transcript$0.115$0.0051

Review a 500-line pull request$0.098$0.0048

Answer a customer support ticket$0.038$0.0019

Extract structured data from a resume$0.056$0.0027

Debug a stack trace with context$0.084$0.0042

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

Add up to four models, tweak tasks live.