Compare AI models

Specifications
Parameters
21B27B/35B/122B
Context window
128k256k
API pricing
Cheapest input
$0.018AkashML—
Cheapest output
$0.09AkashML—
$8.10Darkbloom · fp8—
Benchmarks
SWE-Bench Verified
60.7%72%
Humanity's Last Exam · no tools
10.9%25.3%
Humanity's Last Exam · with tools
17.3%47.5%
GPQA Diamond
71.5%86.6%
Overview
CompanyOpenAIQwen
Release dateAug 5 2025Feb 24 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads gpt-oss-20b on 4 of the 4 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond). gpt-oss-20b shipped 203 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

gpt-oss-20b has 21B parameters, while Qwen3.5 Medium has 27B/35B/122B. Context windows are 128k (gpt-oss-20b) vs 256k (Qwen3.5 Medium).

On SWE-Bench Verified, Qwen3.5 Medium leads at 72% vs gpt-oss-20b at 60.7%. On Humanity's Last Exam · no tools, Qwen3.5 Medium leads at 25.3% vs gpt-oss-20b at 10.9%. On Humanity's Last Exam · with tools, Qwen3.5 Medium leads at 47.5% vs gpt-oss-20b at 17.3%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs gpt-oss-20b at 71.5%.