Compare AI models

Specifications
Parameters
120B>1T
Context window
1M256k
API pricing
Cheapest input
$0.00Nvidia—
Cheapest output
$0.00Nvidia—
$29.50Darkbloom · nvfp4—
Benchmarks
SWE-Bench Verified
71.1%75.3%
LiveCodeBench
88.22%85.9%
Humanity's Last Exam · text only, no tools
31.79%30.2%
GPQA Diamond
89.52%87.4%
IFBench
70.86%70.9%
Overview
CompanyNVIDIAQwen
Release dateOct 15 2026Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Nemotron 3.5 Super VL leads Qwen3-Max-Thinking on 3 of the 5 benchmarks they both report. Qwen3-Max-Thinking shipped 262 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-Max-Thinking has >1T. Context windows are 1M (Nemotron 3.5 Super VL) vs 256k (Qwen3-Max-Thinking). Nemotron 3.5 Super VL is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Nemotron 3.5 Super VL at 71.1%. On LiveCodeBench, Nemotron 3.5 Super VL leads at 88.22% vs Qwen3-Max-Thinking at 85.9%. On Humanity's Last Exam · text only, no tools, Nemotron 3.5 Super VL leads at 31.79% vs Qwen3-Max-Thinking at 30.2%. On GPQA Diamond, Nemotron 3.5 Super VL leads at 89.52% vs Qwen3-Max-Thinking at 87.4%. On IFBench, Qwen3-Max-Thinking leads at 70.9% vs Nemotron 3.5 Super VL at 70.86%.