Compare

Llama 4 Scout vs Claude Sonnet 4.6

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

Verdict

Claude Sonnet 4.6 leads on LMSYS ELO (1368 vs 1265). Llama 4 Scout is ~13.0× cheaper on a 3:1 input:output blend. Llama 4 Scout is open-weights, the other is proprietary.

Meta

Llama 4 Scout

The 70B workhorse open-weight. Fits on a single H100, beloved by self-hosters.

Single-GPU deployableDirt cheap on aggregatorsStrong fine-tuning base

Anthropic

Claude Sonnet 4.6

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$0.35$3.00

Output / 1M$0.80$15.00

Context128K500K

Max output8K64K

LicenseOpen weightsProprietary

Released2025-12-102025-11-04

Benchmarks

LMSYS ELO1265.01368.0

MMLU Pro77.288.7

HumanEval82.492.1

SWE-Bench—64.5

MATH72.585.0

GPQA—59.4

MMMU—74.1

IFEval84.190.5

Per-task cost

Summarize a 1-hour meeting transcript$0.0057$0.052

Review a 500-line pull request$0.0044$0.054

Answer a customer support ticket$0.0017$0.021

Extract structured data from a resume$0.0026$0.030

Debug a stack trace with context$0.0037$0.048

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

Tool

Interactive compare →

Add up to four models, tweak tasks live.