Compare

Claude Sonnet 4.6 vs Claude Opus 4.7

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

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

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$3.00$15.00

Output / 1M$15.00$75.00

Context500K1.0M

Max output64K64K

LicenseProprietaryProprietary

Released2025-11-042026-03-12

Benchmarks

LMSYS ELO1368.01412.0

MMLU Pro88.792.8

HumanEval92.194.4

SWE-Bench64.572.1

MATH85.089.3

GPQA59.466.4

MMMU74.179.2

IFEval90.592.1

Per-task cost

Summarize a 1-hour meeting transcript$0.052$0.263

Review a 500-line pull request$0.054$0.270

Answer a customer support ticket$0.021$0.105

Extract structured data from a resume$0.030$0.150

Debug a stack trace with context$0.048$0.240

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

Add up to four models, tweak tasks live.