Compare AI models

Specifications
Parameters
120B27B
Context window
1M256k
API pricing
Cheapest input
$0.00Nvidia—
Cheapest output
$0.00Nvidia—
$29.50Darkbloom · nvfp4—
Benchmarks
SWE-Bench Verified
71.1%77.2%
SWE-Bench Multilingual
67.72%71.3%
LiveCodeBench
88.22%83.9%
Humanity's Last Exam · no tools
29.2%24%
GPQA Diamond
89.52%87.8%
CharXiv Reasoning
80.82%78.4%
Overview
CompanyNVIDIAQwen
Release dateOct 15 2026Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3.5 Super VL leads Qwen3.6-27B on 4 of the 6 benchmarks they both report. Qwen3.6-27B shipped 176 days before Nemotron 3.5 Super VL, so benchmark comparisons should account for the intervening progress.

Nemotron 3.5 Super VL has 120B parameters, while Qwen3.6-27B has 27B. Context windows are 1M (Nemotron 3.5 Super VL) vs 256k (Qwen3.6-27B).

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs Nemotron 3.5 Super VL at 71.1%. On SWE-Bench Multilingual, Qwen3.6-27B leads at 71.3% vs Nemotron 3.5 Super VL at 67.72%. On LiveCodeBench, Nemotron 3.5 Super VL leads at 88.22% vs Qwen3.6-27B at 83.9%. On Humanity's Last Exam · no tools, Nemotron 3.5 Super VL leads at 29.2% vs Qwen3.6-27B at 24%. On GPQA Diamond, Nemotron 3.5 Super VL leads at 89.52% vs Qwen3.6-27B at 87.8%. On CharXiv Reasoning, Nemotron 3.5 Super VL leads at 80.82% vs Qwen3.6-27B at 78.4%.