Compare

Claude Opus 4.7 vs Claude Sonnet 4.6

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

Verdict

Claude Opus 4.7 leads on LMSYS ELO (1412 vs 1368). Claude Sonnet 4.6 is ~5.0× 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

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

Pricing

Input / 1M$15.00$3.00

Output / 1M$75.00$15.00

Context1.0M500K

Max output64K64K

LicenseProprietaryProprietary

Released2026-03-122025-11-04

Benchmarks

LMSYS ELO1412.01368.0

MMLU Pro92.888.7

HumanEval94.492.1

SWE-Bench72.164.5

MATH89.385.0

GPQA66.459.4

MMMU79.274.1

IFEval92.190.5

Per-task cost

Summarize a 1-hour meeting transcript$0.263$0.052

Review a 500-line pull request$0.270$0.054

Answer a customer support ticket$0.105$0.021

Extract structured data from a resume$0.150$0.030

Debug a stack trace with context$0.240$0.048

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

Add up to four models, tweak tasks live.