Compare

GPT-5 Turbo vs Claude Opus 4.7

OpenAI vs Anthropic. 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.

OpenAI

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

Native multimodalStrong math and scienceHuge ecosystem

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

Pricing

Input / 1M$6.00$15.00

Output / 1M$24.00$75.00

Context400K1.0M

Max output32K64K

LicenseProprietaryProprietary

Released2026-01-212026-03-12

Benchmarks

LMSYS ELO1398.01412.0

MMLU Pro91.292.8

HumanEval93.094.4

SWE-Bench65.872.1

MATH91.589.3

GPQA68.166.4

MMMU78.879.2

IFEval88.992.1

Per-task cost

Summarize a 1-hour meeting transcript$0.102$0.263

Review a 500-line pull request$0.096$0.270

Answer a customer support ticket$0.037$0.105

Extract structured data from a resume$0.054$0.150

Debug a stack trace with context$0.084$0.240

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

Add up to four models, tweak tasks live.