Compare

Claude Sonnet 4.6 vs Gemini 2.5 Ultra

Anthropic 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 1368). Claude Sonnet 4.6 is ~1.8× cheaper on a 3:1 input:output blend.

Anthropic

The workhorse. Near-Opus quality at 1/5 the cost. The default choice for production code and agent workloads.

Excellent cost/quality ratioFast inferenceGreat for Cursor/Claude Code

Google DeepMind

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$3.00$7.00

Output / 1M$15.00$21.00

Context500K2.0M

Max output64K64K

LicenseProprietaryProprietary

Released2025-11-042026-02-05

Benchmarks

LMSYS ELO1368.01385.0

MMLU Pro88.790.4

HumanEval92.190.2

SWE-Bench64.558.3

MATH85.092.0

GPQA59.4—

MMMU74.182.1

IFEval90.589.7

Per-task cost

Summarize a 1-hour meeting transcript$0.052$0.115

Review a 500-line pull request$0.054$0.098

Answer a customer support ticket$0.021$0.038

Extract structured data from a resume$0.030$0.056

Debug a stack trace with context$0.048$0.084

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

Add up to four models, tweak tasks live.