Compare AI models

Specifications
Parameters
—0.8B/2B/4B/9B
Context window
200k256k
API pricing
Cheapest input
$15.00Amazon Bedrock—
Cheapest output
$75.00Amazon Bedrock—
$6,750Amazon Bedrock—
Benchmarks
GPQA Diamond
80.9%81.7%
OSWorld-Verified
44.4%41.8%
MMMU
77.1%78.4%
Overview
CompanyAnthropicQwen
Release dateAug 5 2025Mar 2 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Small leads Claude Opus 4.1 on 2 of the 3 benchmarks they both report (GPQA Diamond, OSWorld-Verified, MMMU). Claude Opus 4.1 shipped 209 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude Opus 4.1) vs 256k (Qwen3.5 Small). Claude Opus 4.1 is closed, while Qwen3.5 Small is open weight.

On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs Claude Opus 4.1 at 80.9%. On OSWorld-Verified, Claude Opus 4.1 leads at 44.4% vs Qwen3.5 Small at 41.8%. On MMMU, Qwen3.5 Small leads at 78.4% vs Claude Opus 4.1 at 77.1%.