Compare AI models

Specifications
Parameters
30B27B/35B/122B
Context window
1M256k
API pricing
Cheapest input
$0.06Nebius—
Cheapest output
$0.24Nebius—
$24.00Nebius · fp8—
Benchmarks
SWE-Bench Verified
38.8%72%
LiveCodeBench
68.25%78.9%
BrowseComp
13.74%63.8%
GPQA Diamond
73.04%86.6%
MMLU-Pro
78.3%86.7%
Overview
CompanyNVIDIAQwen
Release dateDec 15 2025Feb 24 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads Nemotron 3 Nano on 5 of the 5 benchmarks they both report. Nemotron 3 Nano shipped 71 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Nano has 30B parameters, while Qwen3.5 Medium has 27B/35B/122B. Context windows are 1M (Nemotron 3 Nano) vs 256k (Qwen3.5 Medium).

On SWE-Bench Verified, Qwen3.5 Medium leads at 72% vs Nemotron 3 Nano at 38.8%. On LiveCodeBench, Qwen3.5 Medium leads at 78.9% vs Nemotron 3 Nano at 68.25%. On BrowseComp, Qwen3.5 Medium leads at 63.8% vs Nemotron 3 Nano at 13.74%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs Nemotron 3 Nano at 73.04%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs Nemotron 3 Nano at 78.3%.