Compare

Claude Opus 4.7 vs Claude Haiku 4.5

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 1305). Claude Haiku 4.5 is ~18.8× 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

Fast, cheap, and smart enough for most routing and extraction tasks. Great base model for subagents.

Sub-second latency10x cheaper than OpusStrong structured output

Pricing

Input / 1M$15.00$0.80

Output / 1M$75.00$4.00

Context1.0M200K

Max output64K16K

LicenseProprietaryProprietary

Released2026-03-122025-10-01

Benchmarks

LMSYS ELO1412.01305.0

MMLU Pro92.881.4

HumanEval94.487.0

SWE-Bench72.149.2

MATH89.376.8

GPQA66.4—

MMMU79.2—

IFEval92.187.3

Per-task cost

Summarize a 1-hour meeting transcript$0.263$0.014

Review a 500-line pull request$0.270$0.014

Answer a customer support ticket$0.105$0.0056

Extract structured data from a resume$0.150$0.0080

Debug a stack trace with context$0.240$0.013

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

Add up to four models, tweak tasks live.