Compare AI models

Specifications
Parameters
253B0.8B/2B/4B/9B
Context window
128k256k
Benchmarks
LiveCodeBench
66.31%65.6%
GPQA Diamond
76.01%81.7%
Overview
CompanyNVIDIAQwen
Release dateApr 7 2025Mar 2 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama Nemotron Ultra 253B and Qwen3.5 Small are evenly matched across the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Llama Nemotron Ultra 253B shipped 329 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.

Llama Nemotron Ultra 253B has 253B parameters, while Qwen3.5 Small has 0.8B/2B/4B/9B. Context windows are 128k (Llama Nemotron Ultra 253B) vs 256k (Qwen3.5 Small).

On LiveCodeBench, Llama Nemotron Ultra 253B leads at 66.31% vs Qwen3.5 Small at 65.6%. On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs Llama Nemotron Ultra 253B at 76.01%.