Compare AI models

Specifications
Parameters
550B>1T
Context window
1M256k
API pricing
Cheapest input
$0.40DeepInfra—
Cheapest output
$1.76DeepInfra—
$210KT—
Benchmarks
SWE-Bench Verified
71.9%75.3%
LiveCodeBench
89%85.9%
Humanity's Last Exam · text only, no tools
29.24%30.2%
GPQA Diamond
87%87.4%
IFBench
82.94%70.9%
MMLU-Pro
86.8%85.7%
Overview
CompanyNVIDIAQwen
Release dateJun 4 2026Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Nemotron 3 Ultra and Qwen3-Max-Thinking are evenly matched across the 6 benchmarks they both report. Qwen3-Max-Thinking shipped 129 days before Nemotron 3 Ultra, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Ultra has 550B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 1M (Nemotron 3 Ultra) vs 256k (Qwen3-Max-Thinking). Nemotron 3 Ultra is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Nemotron 3 Ultra at 71.9%. On LiveCodeBench, Nemotron 3 Ultra leads at 89% vs Qwen3-Max-Thinking at 85.9%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs Nemotron 3 Ultra at 29.24%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Nemotron 3 Ultra at 87%. On IFBench, Nemotron 3 Ultra leads at 82.94% vs Qwen3-Max-Thinking at 70.9%. On MMLU-Pro, Nemotron 3 Ultra leads at 86.8% vs Qwen3-Max-Thinking at 85.7%.