Compare AI models

Specifications
Parameters
120B>1T
Context window
1M256k
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.32DeepInfra—
$35.00DeepInfra · bf16—
Benchmarks
SWE-Bench Verified
60.47%75.3%
LiveCodeBench
81.19%85.9%
Humanity's Last Exam · text only, no tools
20.3%30.2%
GPQA Diamond
79.23%87.4%
MMLU-Pro
83.73%85.7%
Overview
CompanyNVIDIAQwen
Release dateMar 11 2026Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Nemotron 3 Super on 5 of the 5 benchmarks they both report. Qwen3-Max-Thinking shipped 44 days before Nemotron 3 Super, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Super has 120B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 1M (Nemotron 3 Super) vs 256k (Qwen3-Max-Thinking). Nemotron 3 Super is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Nemotron 3 Super at 60.47%. On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs Nemotron 3 Super at 81.19%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs Nemotron 3 Super at 20.3%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Nemotron 3 Super at 79.23%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Nemotron 3 Super at 83.73%.