Compare AI models

Specifications
Parameters
120B4B/30B/235B
Context window
1M256k
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.32DeepInfra—
$35.00DeepInfra · bf16—
Benchmarks
LiveCodeBench
81.19%74.1%
Humanity's Last Exam · text only, no tools
20.3%18.2%
AIME 2025
90.21%92.3%
GPQA Diamond
79.23%81.1%
MMLU-Pro
83.73%84.4%
Overview
CompanyNVIDIAQwen
Release dateMar 11 2026Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Nemotron 3 Super on 3 of the 5 benchmarks they both report. Qwen3-2507 shipped 233 days before Nemotron 3 Super, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Super has 120B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 1M (Nemotron 3 Super) vs 256k (Qwen3-2507).

On LiveCodeBench, Nemotron 3 Super leads at 81.19% vs Qwen3-2507 at 74.1%. On Humanity's Last Exam · text only, no tools, Nemotron 3 Super leads at 20.3% vs Qwen3-2507 at 18.2%. On AIME 2025, Qwen3-2507 leads at 92.3% vs Nemotron 3 Super at 90.21%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Nemotron 3 Super at 79.23%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Nemotron 3 Super at 83.73%.