Compare AI models

Specifications
Parameters
30B4B/30B/235B
Context window
1M256k
API pricing
Cheapest input
$0.06Nebius—
Cheapest output
$0.24Nebius—
$24.00Nebius · fp8—
Benchmarks
LiveCodeBench
68.25%74.1%
Humanity's Last Exam · text only, no tools
10.89%18.2%
AIME 2025
89.06%92.3%
GPQA Diamond
73.04%81.1%
MMLU-Pro
78.3%84.4%
Overview
CompanyNVIDIAQwen
Release dateDec 15 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Nemotron 3 Nano on 5 of the 5 benchmarks they both report. Qwen3-2507 shipped 147 days before Nemotron 3 Nano, so benchmark comparisons should account for the intervening progress.

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

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Nemotron 3 Nano at 68.25%. On Humanity's Last Exam · text only, no tools, Qwen3-2507 leads at 18.2% vs Nemotron 3 Nano at 10.89%. On AIME 2025, Qwen3-2507 leads at 92.3% vs Nemotron 3 Nano at 89.06%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Nemotron 3 Nano at 73.04%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Nemotron 3 Nano at 78.3%.