Compare

DeepSeek R2 vs Gemini 2.5 Flash

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

Verdict

Gemini 2.5 Flash is ~1.8× cheaper on a 3:1 input:output blend. DeepSeek R2 is open-weights, the other is proprietary.

DeepSeek

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

Frontier math at open-weights pricingLong CoT traces

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$0.55$0.30

Output / 1M$2.19$1.20

Context128K1.0M

Max output64K32K

LicenseOpen weightsProprietary

Released2026-01-152026-02-05

Benchmarks

LMSYS ELO—1312.0

MMLU Pro87.882.1

HumanEval90.185.8

MATH94.184.2

GPQA71.2—

MMMU—74.6

IFEval—86.1

Per-task cost

Summarize a 1-hour meeting transcript$0.0093$0.0051

Review a 500-line pull request$0.0088$0.0048

Answer a customer support ticket$0.0034$0.0019

Extract structured data from a resume$0.0049$0.0027

Debug a stack trace with context$0.0077$0.0042

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

Add up to four models, tweak tasks live.