Compare AI models

Specifications
Parameters
—27B/35B/122B
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%72%
Terminal-Bench 2.0
59.1%49.4%
BrowseComp
76.2%63.8%
Humanity's Last Exam · no tools
33.2%25.3%
Humanity's Last Exam · with tools
49%47.5%
GPQA Diamond
89.9%86.6%
OSWorld-Verified
72.5%58%
CharXiv Reasoning
72.4%77.2%
MMMU-Pro
74.5%76.9%
Overview
CompanyAnthropicQwen
Release dateFeb 17 2026Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Sonnet 4.6 leads Qwen3.5 Medium on 7 of the 9 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 Qwen3.5 Medium. Claude Sonnet 4.6 shipped 7 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Sonnet 4.6) vs 256k (Qwen3.5 Medium). Claude Sonnet 4.6 is closed, while Qwen3.5 Medium is open weight.

On SWE-Bench Verified, Claude Sonnet 4.6 leads at 79.6% vs Qwen3.5 Medium at 72%. On Terminal-Bench 2.0, Claude Sonnet 4.6 leads at 59.1% vs Qwen3.5 Medium at 49.4%. On BrowseComp, Claude Sonnet 4.6 leads at 76.2% vs Qwen3.5 Medium at 63.8%. On Humanity's Last Exam · no tools, Claude Sonnet 4.6 leads at 33.2% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, Claude Sonnet 4.6 leads at 49% vs Qwen3.5 Medium at 47.5%. On GPQA Diamond, Claude Sonnet 4.6 leads at 89.9% vs Qwen3.5 Medium at 86.6%. On OSWorld-Verified, Claude Sonnet 4.6 leads at 72.5% vs Qwen3.5 Medium at 58%. On CharXiv Reasoning, Qwen3.5 Medium leads at 77.2% vs Claude Sonnet 4.6 at 72.4%. On MMMU-Pro, Qwen3.5 Medium leads at 76.9% vs Claude Sonnet 4.6 at 74.5%.