Compare AI models

Specifications
Parameters
—27B
Context window
1M256k
API pricing
Input price
$0.10—
Output price
$0.50—
Cached input price
$0.01—
Cheapest input
$0.10Amazon Bedrock—
Cheapest output
$0.50Amazon Bedrock—
$45.00Anthropic list price—
Benchmarks
SWE-Bench Multilingual
83.7%71.3%
Humanity's Last Exam · no tools
45.9%24%
Overview
CompanyAnthropicQwen
Release dateOct 7 2026Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Haiku 5.5 leads Qwen3.6-27B on 2 of the 2 benchmarks they both report (SWE-Bench Multilingual, Humanity's Last Exam). Only Claude Haiku 5.5 has a verified first-party price for an available API: $0.10 per million input tokens and $0.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Qwen3.6-27B shipped 168 days before Claude Haiku 5.5, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Haiku 5.5) vs 256k (Qwen3.6-27B). Claude Haiku 5.5 is closed, while Qwen3.6-27B is open weight.

On SWE-Bench Multilingual, Claude Haiku 5.5 leads at 83.7% vs Qwen3.6-27B at 71.3%. On Humanity's Last Exam · no tools, Claude Haiku 5.5 leads at 45.9% vs Qwen3.6-27B at 24%.