Compare

Claude Sonnet 4.6 vs Llama 4 Behemoth

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

Verdict

Claude Sonnet 4.6 leads on LMSYS ELO (1368 vs 1342). Llama 4 Behemoth is ~1.5× cheaper on a 3:1 input:output blend. Llama 4 Behemoth is open-weights, the other is proprietary.

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

Meta

Llama 4 Behemoth

Meta’s open-weights flagship. 405B params, fully open license, runs on every major inference provider.

Best open-weights modelRuns anywhereTransparent training

Pricing

Input / 1M$3.00$2.50

Output / 1M$15.00$8.00

Context500K256K

Max output64K16K

LicenseProprietaryOpen weights

Released2025-11-042025-12-10

Benchmarks

LMSYS ELO1368.01342.0

MMLU Pro88.787.1

HumanEval92.189.3

SWE-Bench64.552.4

MATH85.081.5

GPQA59.456.2

MMMU74.1—

IFEval90.588.0

Per-task cost

Summarize a 1-hour meeting transcript$0.052$0.041

Review a 500-line pull request$0.054$0.036

Answer a customer support ticket$0.021$0.014

Extract structured data from a resume$0.030$0.021

Debug a stack trace with context$0.048$0.031

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.