Compare AI models

Specifications
Parameters
—27B
Context window
200k256k
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
77.2%77.2%
Terminal-Bench 2.0
51%59.3%
Humanity's Last Exam · no tools
17.7%24%
GPQA Diamond
83.4%87.8%
MMMU-Pro
63.4%75.8%
MMMU
77.8%82.9%
Overview
CompanyAnthropicQwen
Release dateSep 29 2025Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Claude Sonnet 4.5 on 5 of the 6 benchmarks they both report. Only Claude Sonnet 4.5 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 4.5 shipped 205 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude Sonnet 4.5) vs 256k (Qwen3.6-27B). Claude Sonnet 4.5 is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Verified, both models score 77.2%. On Terminal-Bench 2.0, Qwen3.6-27B leads at 59.3% vs Claude Sonnet 4.5 at 51%. On Humanity's Last Exam · no tools, Qwen3.6-27B leads at 24% vs Claude Sonnet 4.5 at 17.7%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Claude Sonnet 4.5 at 83.4%. On MMMU-Pro, Qwen3.6-27B leads at 75.8% vs Claude Sonnet 4.5 at 63.4%. On MMMU, Qwen3.6-27B leads at 82.9% vs Claude Sonnet 4.5 at 77.8%.