Compare

Gemini 2.5 Ultra vs DeepSeek V4

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

Verdict

Gemini 2.5 Ultra leads on LMSYS ELO (1385 vs 1334). DeepSeek V4 is ~60.0× cheaper on a 3:1 input:output blend. DeepSeek V4 is open-weights, the other is proprietary.

Google DeepMind

Gemini 2.5 Ultra

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

2M context windowNative videoBest multimodal reasoning

DeepSeek

DeepSeek V4

The shock-the-market moment of 2026. Frontier coding quality at 1/50th the price of Opus.

Unbeatable $/qualityOpen weightsGreat at code

Pricing

Input / 1M$7.00$0.14

Output / 1M$21.00$0.28

Context2.0M128K

Max output64K16K

LicenseProprietaryOpen weights

Released2026-02-052026-02-20

Benchmarks

LMSYS ELO1385.01334.0

MMLU Pro90.485.4

HumanEval90.291.5

SWE-Bench58.354.1

MATH92.088.7

MMMU82.1—

IFEval89.785.8

Per-task cost

Summarize a 1-hour meeting transcript$0.115$0.0022

Review a 500-line pull request$0.098$0.0017

Answer a customer support ticket$0.038$0.0006

Extract structured data from a resume$0.056$0.0010

Debug a stack trace with context$0.084$0.0014

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

Tool

Interactive compare →

Add up to four models, tweak tasks live.