Compare AI models

Specifications
Parameters
550B27B
Context window
1M256k
API pricing
Cheapest input
$0.40DeepInfra—
Cheapest output
$1.76DeepInfra—
$210KT—
Benchmarks
SWE-Bench Verified
71.9%77.2%
SWE-Bench Multilingual
67.7%71.3%
LiveCodeBench
89%83.9%
GPQA Diamond
87%87.8%
MMLU-Pro
86.8%86.2%
Overview
CompanyNVIDIAQwen
Release dateJun 4 2026Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Nemotron 3 Ultra on 3 of the 5 benchmarks they both report. Qwen3.6-27B shipped 43 days before Nemotron 3 Ultra, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Ultra has 550B parameters, while Qwen3.6-27B has 27B. Context windows are 1M (Nemotron 3 Ultra) vs 256k (Qwen3.6-27B).

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs Nemotron 3 Ultra at 71.9%. On SWE-Bench Multilingual, Qwen3.6-27B leads at 71.3% vs Nemotron 3 Ultra at 67.7%. On LiveCodeBench, Nemotron 3 Ultra leads at 89% vs Qwen3.6-27B at 83.9%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Nemotron 3 Ultra at 87%. On MMLU-Pro, Nemotron 3 Ultra leads at 86.8% vs Qwen3.6-27B at 86.2%.