Compare AI models

Specifications
Parameters
—0.8B/2B/4B/9B
Context window
1M256k
API pricing
Cheapest input
$0.10Azure—
Cheapest output
$0.40Azure—
$40.00Azure—
Benchmarks
IFEval
74.5%91.5%
GPQA Diamond
50.3%81.7%
CharXiv Reasoning
40.5%73%
MMMU
55.4%78.4%
Overview
CompanyOpenAIQwen
Release dateApr 14 2025Mar 2 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Small leads GPT-4.1 nano on 4 of the 4 benchmarks they both report (IFEval, GPQA Diamond, CharXiv Reasoning, MMMU). GPT-4.1 nano shipped 322 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (GPT-4.1 nano) vs 256k (Qwen3.5 Small). GPT-4.1 nano is closed, while Qwen3.5 Small is open weight.

On IFEval, Qwen3.5 Small leads at 91.5% vs GPT-4.1 nano at 74.5%. On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs GPT-4.1 nano at 50.3%. On CharXiv Reasoning, Qwen3.5 Small leads at 73% vs GPT-4.1 nano at 40.5%. On MMMU, Qwen3.5 Small leads at 78.4% vs GPT-4.1 nano at 55.4%.