Llama 3.3 Nemotron Super (Nonthinking)

Release Date: Mar 18, 2025

Developer NVIDIA 🇺🇸

Context Window 131k

Max Output Tokens 33k

Token Costs (in/out) $0.00/0.00

Weights Open

Input Modalities

Accuracy

53.76 %

Avg. Cost (In/Out)

N/A

Latency

24.12 s

BenchmarksAccuracyRankings

0.0%

±0.96

131/145

0.0%

±2.47

127/138

0.0%

±1.04

136/143

0.0%

±0.45

119/138

Proprietary BenchmarksAcademic BenchmarksIndustry Partners

View Hyperparameter Settings

Default Provider : NVIDIA

Temperature: Default

Top P: Default

Top K: Default

Max Output Tokens: 32,768