HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/nvidia/nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16

nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16

family nemotron · 1 variants · unknown

provider
nvidia
released
—
huggingface
https://huggingface.co/nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16
best scores
MMLU: 78.56MMLU-Pro: 62.59ARC-Challenge: 91.72WinoGrande: 76.09HumanEval: 79.27MBPP: 74.71GSM8K: 92.49MATH-500: 84.4MGSM: 80.8QuALITY: 100.0

Best scores per benchmark

benchmarkcategorybest score
QuALITYknowledge100.0
GSM8Kmath92.49
ARC-Challengeknowledge91.72
MATH-500math84.4
MGSMmath80.8
HumanEvalcoding79.27
MMLUknowledge78.56
WinoGrandeknowledge76.09
MBPPcoding74.71
MMLU-Proknowledge62.59

Variants (1)

variantkindquantbitsvRAMdlorgyear
Nemotron-Labs-TwoTower-30B-A3B-Base-BF16originalbf1616.04,375nvidia2026
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.