NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

Home/Models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

kind: original
quant: bf16 (16-bit)
family: nemotron
modality: text-generation
root model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16
provider: nvidia
license: other
language: en, fr, es, it, de, pt, ja, ko, hi, ar, zh, he
context: 1M
library: transformers
vRAM (GB): —
size on disk: —
downloads: 801
likes: 29
created: —
last modified: 2026-06-05T17:57:11+00:00 (2026)
huggingface: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16
tags: transformerssafetensorsnemotron_htext-generationnvidiapytorchnemotron-3latent-moemtpenfresitdeptjakohiarzhhelicense:otherendpoints_compatibleregion:us

Benchmark scores (21)

benchmark	category	score	context	conf	evidence
ARC-Challenge	knowledge	97.35	ARC-Challenge	medium	`\| ARC-Challenge \| 25-shot, acc_norm \| 97.35 \| 95.22 \| 97.27 \| 95.82 \| 96.59 \|`
RULER	long-context	95.3	RULER 64K	medium	`\| RULER 64K \| 0-shot \| 95.30 \| 93.30 \| 90.11 \| 93.79 \| 16.12 \|`
RULER	long-context	92.49	RULER 128K	medium	`\| RULER 128K \| 0-shot \| 92.49 \| 91.88 \| 55.77 \| 88.61 \| 0.00 \|`
HellaSwag	knowledge	90.51	HellaSwag	medium	`\| HellaSwag \| 10-shot, acc_norm \| 90.51 \| 89.44 \| 88.88 \| 90.92 \| 90.17 \|`
MMLU	knowledge	90.13	MMLU Global Lite	medium	`\| MMLU Global Lite \| 5-shot, avg \| 90.13 \| 85.59 \| 87.34 \| 85.63 \| 85.81 \|`
MMLU	knowledge	89.08	MMLU	medium	`\| MMLU \| 5-shot, acc \| 89.08 \| 87.82 \| 87.35 \| 87.60 \| 86.50 \|`
GSM8K	math	88.1	GSM8K	medium	`\| GSM8K \| 8-shot, CoT EM \| 88.10 \| 84.38 \| 91.21 \| 91.05 \| 85.37 \|`
MGSM	math	87.73	MGSM	medium	`\| MGSM \| 8-shot, native CoT avg \| 87.73 \| 82.33 \| 82.93 \| 85.20 \| 81.27 \|`
RULER	long-context	86.22	RULER 256K	medium	`\| RULER 256K \| 0-shot \| 86.22 \| -- \| 35.50 \| -- \| -- \|`
MBPP	coding	85.97	MBPP-Sanitized	medium	`\| MBPP-Sanitized \| 3-shot pass@1 n=32, EvalPlus sanitized \| 85.97 \| 58.66 \| 84.08 \| 72.14 \| 76.69 \|`
RULER	long-context	84.54	RULER 512K	medium	`\| RULER 512K \| 0-shot \| 84.54 \| -- \| -- \| -- \| -- \|`
HumanEval	coding	83.84	HumanEval	medium	`\| HumanEval \| sampled pass@1 n=32, EvalPlus sanitized \| 83.84 \| 61.85 \| 66.71 \| 78.20 \| 78.16 \|`
PIQA	knowledge	83.79	PIQA	medium	`\| PIQA \| 0-shot, acc_norm \| 83.79 \| 85.09 \| 84.82 \| 85.47 \| 85.09 \|`
MATH	math	82.0	MATH	medium	`\| MATH \| 4-shot, EM \| 82.00 \| 60.12 \| 62.88 \| 68.40 \| 57.58 \|`
WinoGrande	knowledge	79.32	WinoGrande	medium	`\| WinoGrande \| 5-shot, acc \| 79.32 \| 83.43 \| 82.08 \| 84.21 \| 85.24 \|`
MMLU-Pro	knowledge	79.07	MMLU-Pro	medium	`\| MMLU-Pro \| 5-shot, CoT EM \| 79.07 \| 63.26 \| 67.42 \| 69.15 \| 65.78 \|`
AGIEval	reasoning	78.73	AGIEval-En	medium	`\| AGIEval-En \| 3/5-shot, CoT EM \| 78.73 \| 70.13 \| 69.30 \| 72.55 \| 70.06 \|`
RULER	long-context	76.83	RULER 1M	medium	`\| RULER 1M \| 0-shot \| 76.83 \| -- \| -- \| -- \| -- \|`
RULER	long-context	64.0		medium	`RULER 64`
GPQA	reasoning	50.0	GPQA	medium	`\| GPQA \| 5-shot, CoT EM \| 50.00 \| 31.82 \| 34.85 \| 43.43 \| 34.85 \|`
OpenBookQA	knowledge	48.6	OpenBookQA	medium	`\| OpenBookQA \| 0-shot, acc_norm \| 48.60 \| 48.20 \| 51.40 \| 50.80 \| 49.60 \|`

Discussions (0)

none scraped.