Compare

Claude Sonnet 4.6 vs Qwen 3 Max

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

Verdict

Claude Sonnet 4.6 leads on LMSYS ELO (1368 vs 1295). Qwen 3 Max is ~2.1× cheaper on a 3:1 input:output blend. Qwen 3 Max 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

Qwen

Qwen 3 Max

Alibaba’s flagship. Strongest non-English coverage of any open model; dominant in Asian markets.

MultilingualOpen weightsCompetitive coding

Pricing

Input / 1M$3.00$1.60

Output / 1M$15.00$6.40

Context500K128K

Max output64K16K

LicenseProprietaryOpen weights

Released2025-11-042025-11-20

Benchmarks

LMSYS ELO1368.01295.0

MMLU Pro88.784.0

HumanEval92.187.2

SWE-Bench64.5—

MATH85.085.1

GPQA59.4—

MMMU74.171.8

IFEval90.585.5

Per-task cost

Summarize a 1-hour meeting transcript$0.052$0.027

Review a 500-line pull request$0.054$0.026

Answer a customer support ticket$0.021$0.0099

Extract structured data from a resume$0.030$0.014

Debug a stack trace with context$0.048$0.022

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.