Compare AI models

Specifications
Parameters
—27B
Context window
200k256k
API pricing
Cheapest input
$15.00Amazon Bedrock—
Cheapest output
$75.00Amazon Bedrock—
$6,750Amazon Bedrock—
Benchmarks
SWE-Bench Verified
74.5%77.2%
Terminal-Bench 2.0
46.5%59.3%
GPQA Diamond
80.9%87.8%
MMMU
77.1%82.9%
Overview
CompanyAnthropicQwen
Release dateAug 5 2025Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Claude Opus 4.1 on 4 of the 4 benchmarks they both report (SWE-Bench Verified, Terminal-Bench 2.0, GPQA Diamond, MMMU). Claude Opus 4.1 shipped 260 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude Opus 4.1) vs 256k (Qwen3.6-27B). Claude Opus 4.1 is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs Claude Opus 4.1 at 74.5%. On Terminal-Bench 2.0, Qwen3.6-27B leads at 59.3% vs Claude Opus 4.1 at 46.5%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Claude Opus 4.1 at 80.9%. On MMMU, Qwen3.6-27B leads at 82.9% vs Claude Opus 4.1 at 77.1%.