Compare

Claude Opus 4.7 vs GPT-5 Turbo

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

Verdict

Claude Opus 4.7 leads on LMSYS ELO (1412 vs 1398). GPT-5 Turbo is ~2.9× cheaper on a 3:1 input:output blend.

Anthropic

Anthropic’s frontier reasoning model. Leads SWE-Bench and holds top ranks on long-context coding and agentic workflows.

Best-in-class coding agent behaviorStrong instruction following1M-token context with high recallHigh reliability under tool use

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$15.00$6.00

Output / 1M$75.00$24.00

Context1.0M400K

Max output64K32K

LicenseProprietaryProprietary

Released2026-03-122026-01-21

Benchmarks

LMSYS ELO1412.01398.0

MMLU Pro92.891.2

HumanEval94.493.0

SWE-Bench72.165.8

MATH89.391.5

GPQA66.468.1

MMMU79.278.8

IFEval92.188.9

Per-task cost

Summarize a 1-hour meeting transcript$0.263$0.102

Review a 500-line pull request$0.270$0.096

Answer a customer support ticket$0.105$0.037

Extract structured data from a resume$0.150$0.054

Debug a stack trace with context$0.240$0.084

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

Add up to four models, tweak tasks live.