Compare AI models

Specifications
Parameters
—27B
Context window
1M256k
API pricing
Input price
$3.00—
Output price
$15.00—
Cached input price
$0.30—
Cheapest input
$3.00Amazon Bedrock—
Cheapest output
$15.00Amazon Bedrock—
$1,350Anthropic list price—
Benchmarks
SWE-Bench Verified
79.6%77.2%
Terminal-Bench 2.0
59.1%59.3%
Humanity's Last Exam · no tools
33.2%24%
GPQA Diamond
89.9%87.8%
CharXiv Reasoning
72.4%78.4%
MMMU-Pro
74.5%75.8%
Overview
CompanyAnthropicQwen
Release dateFeb 17 2026Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Sonnet 4.6 and Qwen3.6-27B are evenly matched across the 6 benchmarks they both report. Only Claude Sonnet 4.6 has a verified first-party price for an available API: $3.00 per million input tokens and $15.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Claude Sonnet 4.6 shipped 64 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Sonnet 4.6) vs 256k (Qwen3.6-27B). Claude Sonnet 4.6 is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Verified, Claude Sonnet 4.6 leads at 79.6% vs Qwen3.6-27B at 77.2%. On Terminal-Bench 2.0, Qwen3.6-27B leads at 59.3% vs Claude Sonnet 4.6 at 59.1%. On Humanity's Last Exam · no tools, Claude Sonnet 4.6 leads at 33.2% vs Qwen3.6-27B at 24%. On GPQA Diamond, Claude Sonnet 4.6 leads at 89.9% vs Qwen3.6-27B at 87.8%. On CharXiv Reasoning, Qwen3.6-27B leads at 78.4% vs Claude Sonnet 4.6 at 72.4%. On MMMU-Pro, Qwen3.6-27B leads at 75.8% vs Claude Sonnet 4.6 at 74.5%.