Inference Index
Compare

DeepSeek V4 vs Gemini 2.5 Ultra

DeepSeek 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 1334). DeepSeek V4 is ~60.0× cheaper on a 3:1 input:output blend. DeepSeek V4 is open-weights, the other is proprietary.

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
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
Pricing
Input / 1M$0.14$7.00
Output / 1M$0.28$21.00
Context128K2.0M
Max output16K64K
LicenseOpen weightsProprietary
Released2026-02-202026-02-05
Benchmarks
LMSYS ELO1334.01385.0
MMLU Pro85.490.4
HumanEval91.590.2
SWE-Bench54.158.3
MATH88.792.0
MMMU82.1
IFEval85.889.7
Per-task cost
Summarize a 1-hour meeting transcript$0.0022$0.115
Review a 500-line pull request$0.0017$0.098
Answer a customer support ticket$0.0006$0.038
Extract structured data from a resume$0.0010$0.056
Debug a stack trace with context$0.0014$0.084

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