NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16

Home/Models/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16

NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16

kind: original
quant: bf16 (16-bit)
family: nemotron
modality: text-generation
root model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16
provider: nvidia
license: other
language: en, es, fr, de, ja, it, zh, ar, he, hi, ko, cs
context: 1M
library: transformers
vRAM (GB): —
size on disk: —
downloads: 5,939
likes: 32
created: —
last modified: 2026-03-14T14:29:35+00:00 (2026)
huggingface: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16
tags: transformerssafetensorsnemotron_htext-generationnvidiapytorchnemotron-3latent-moemtpcustom_codeenesfrdejaitzharhehikocsdanl

Benchmark scores (23)

benchmark	category	score	context	conf	evidence
ARC-Challenge	knowledge	96.08	ARC-Challenge	medium	`\| ARC-Challenge \| 25-shot, acc_norm \| 96.08 \| 94.80 \| 93.90 \|`
RULER	long-context	93.17	RULER 64K	medium	`\| RULER 64K \| 0-shot \| 93.17 \| — \| 81.58 \|`
GSM8K	math	90.67	GSM8K	medium	`\| GSM8K \| 8-shot, EM \| 90.67 \| 90.75 \| 82.60 \|`
RULER	long-context	89.0	RULER 128K	medium	`\| RULER 128K \| 0-shot \| 89.00 \| 57.56 \| 63.62 \|`
HellaSwag	knowledge	88.97	HellaSwag	medium	`\| HellaSwag \| 10-shot, acc_norm \| 88.97 \| 84.69 \| 87.70 \|`
MGSM	math	87.47	MGSM	medium	`\| MGSM \| 8-shot, avg \| 87.47 \| 82.73 \| 80.33 \|`
RULER	long-context	86.18	RULER 256K	medium	`\| RULER 256K \| 0-shot \| 86.18 \| — \| — \|`
MMLU	knowledge	86.01	MMLU	medium	`\| MMLU \| 5-shot, acc \| 86.01 \| 81.00 \| 81.00 \|`
MMLU	knowledge	85.72	MMLU Global Lite	medium	`\| MMLU Global Lite \| 5-shot, avg \| 85.72 \| 74.94 \| 79.25 \|`
PIQA	knowledge	85.47	PIQA	medium	`\| PIQA \| 0-shot, acc_norm \| 85.47 \| 84.00 \| 84.22 \|`
MATH	math	84.84	MATH	medium	`\| MATH \| 4-shot, EM \| 84.84 \| 63.80 \| 50.36 \|`
RULER	long-context	82.16	RULER 512K	medium	`\| RULER 512K \| 0-shot \| 82.16 \| — \| — \|`
HumanEval	coding	79.4	HumanEval	medium	`\| HumanEval \| 0-shot, pass@1 n=32 \| 79.40 \| 70.10 \| 76.30 \|`
WinoGrande	knowledge	78.93	WinoGrande	medium	`\| WinoGrande \| 5-shot, acc \| 78.93 \| 78.37 \| 83.82 \|`
MBPP	coding	78.38	MBPP-Sanitized	medium	`\| MBPP-Sanitized \| 3-shot, pass@1 n=32 \| 78.38 \| 77.30 \| 77.50 \|`
AGIEval	reasoning	77.92	AGIEval-En	medium	`\| AGIEval-En \| 3/5-shot, CoT EM \| 77.92 \| 61.70 \| 62.40 \|`
MMLU-Pro	knowledge	75.65	MMLU-Pro	medium	`\| MMLU-Pro \| 5-shot, CoT EM \| 75.65 \| 62.10 \| 58.20 \|`
RULER	long-context	74.39	RULER 1M	medium	`\| RULER 1M \| 0-shot \| 74.39 \| — \| — \|`
MATH	math	70.0	MATH Level 5	medium	`\| MATH Level 5 \| 4-shot, EM \| 70.00 \| 39.80 \| 26.30 \|`
RULER	long-context	64.0		medium	`RULER 64`
GPQA Diamond	reasoning	60.0	GPQA-Diamond	medium	`\| GPQA-Diamond \| 5-shot, CoT EM \| 60.00 \| 36.00 \| 23.20 \|`
AIME 2024	math	53.33	AIME 2024	medium	`\| AIME 2024 \| pass@32 \| 53.33 \| 30.00 \| 20.00 \|`
OpenBookQA	knowledge	50.2	OpenBookQA	medium	`\| OpenBookQA \| 0-shot, acc_norm \| 50.20 \| 47.00 \| 48.60 \|`

Discussions (0)

none scraped.