Compare

Gemini 2.5 Ultra vs DeepSeek R2

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

Verdict

DeepSeek R2 is ~10.9× cheaper on a 3:1 input:output blend. DeepSeek R2 is open-weights, the other is proprietary.

Google DeepMind

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

2M context windowNative videoBest multimodal reasoning

DeepSeek

DeepSeek’s reasoning variant. Competes with o4 on math at a fraction of the cost.

Frontier math at open-weights pricingLong CoT traces

Pricing

Input / 1M$7.00$0.55

Output / 1M$21.00$2.19

Context2.0M128K

Max output64K64K

LicenseProprietaryOpen weights

Released2026-02-052026-01-15

Benchmarks

LMSYS ELO1385.0—

MMLU Pro90.487.8

HumanEval90.290.1

SWE-Bench58.3—

MATH92.094.1

GPQA—71.2

MMMU82.1—

IFEval89.7—

Per-task cost

Summarize a 1-hour meeting transcript$0.115$0.0093

Review a 500-line pull request$0.098$0.0088

Answer a customer support ticket$0.038$0.0034

Extract structured data from a resume$0.056$0.0049

Debug a stack trace with context$0.084$0.0077

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

Add up to four models, tweak tasks live.