Compare AI models

Specifications
Parameters
—0.8B/2B/4B/9B
Context window
1M256k
Benchmarks
GPQA Diamond
94.5%81.7%
OSWorld-Verified
79.6%41.8%
CharXiv Reasoning
86.1%73%
Overview
CompanyAnthropicQwen
Release dateApr 7 2026Mar 2 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Mythos Preview leads Qwen3.5 Small on 3 of the 3 benchmarks they both report (GPQA Diamond, OSWorld-Verified, CharXiv Reasoning). Qwen3.5 Small shipped 36 days before Claude Mythos Preview, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Mythos Preview) vs 256k (Qwen3.5 Small). Claude Mythos Preview is closed, while Qwen3.5 Small is open weight.

On GPQA Diamond, Claude Mythos Preview leads at 94.5% vs Qwen3.5 Small at 81.7%. On OSWorld-Verified, Claude Mythos Preview leads at 79.6% vs Qwen3.5 Small at 41.8%. On CharXiv Reasoning, Claude Mythos Preview leads at 86.1% vs Qwen3.5 Small at 73%.