Compare

Claude Sonnet 4.6 vs GPT-5 Turbo

Anthropic vs OpenAI. Specs, benchmarks, and real per-task cost — all in one page.

Verdict

GPT-5 Turbo leads on LMSYS ELO (1398 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

OpenAI

OpenAI’s flagship unified model. Handles text, vision, and audio natively. The generalist benchmark champion.

Native multimodalStrong math and scienceHuge ecosystem

Pricing

Input / 1M$3.00$6.00

Output / 1M$15.00$24.00

Context500K400K

Max output64K32K

LicenseProprietaryProprietary

Released2025-11-042026-01-21

Benchmarks

LMSYS ELO1368.01398.0

MMLU Pro88.791.2

HumanEval92.193.0

SWE-Bench64.565.8

MATH85.091.5

GPQA59.468.1

MMMU74.178.8

IFEval90.588.9

Per-task cost

Summarize a 1-hour meeting transcript$0.052$0.102

Review a 500-line pull request$0.054$0.096

Answer a customer support ticket$0.021$0.037

Extract structured data from a resume$0.030$0.054

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.