Nemotron 3.5 Super VL (120B A12B)
NVIDIA开源权重OpenMDW License v1.1 · 商用许可
描述
NVIDIA Nemotron 3.5 Super VL is an open multimodal 120B total / 12B active Mixture-of-Experts model (hybrid Mamba-2 + Attention with a C-RADIO / RADIO vision encoder) built for long-running agents. It accepts text, image, and video inputs and produces text, with up to 1M context, tool use, and configurable reasoning. Released with open weights under OpenMDW-1.1.
发布日期
2026-10-15
参数规模
120.0B
上下文长度
1.0M
支持模态
image, text, video
能力雷达图
64
general
60
coding
50
reasoning
60
science估算
40
agents
70
multimodal
缺少专门科学评测时，Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
Tau3 Banking
18.9%自报
General
GDPval-AA
1211.00 / 3000自报
Instruction Following
IFBench
70.9%自报
Math
MathVision
78.2%自报
Multimodal
OSWorld-Verified
51.1%自报
Reasoning
GPQANYU + Cohere + Anthropic (2023)
89.5%自报
LiveCodeBench v6
88.2%自报
CharXiv-R
80.8%自报
BrowseCompOpenAI (2025)
78.0%自报
SWE-Bench Verified
71.1%自报
AA-LCR
68.6%自报
SWE-bench Multilingual
67.7%自报
Terminal-Bench 2.1
66.7%自报
SWE-Bench ProPrinceton NLP (2024)
51.8%自报
SciCode
47.1%自报
Humanity's Last Exam
31.8%自报
Science
OmniScience
26.2%自报
Vision
OCRBench-V2 (en)
68.1%自报
MMLongBench-Doc
0.63 / 100自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Legal100
Finance100
Agents100
Reasoning87
General64
Search80
Image To Text70
Instruction Following70
Long Context70
Multimodal70
Physics70
Frontend Development70
Biology70
Chemistry70
Code60
Vision60
Math50
Tool Calling40
Knowledge30
Science30
定价
输入价格$0 / 1M tokens
输出价格$0 / 1M tokens
混合价格(3:1)$0 / 1M tokens
速度
暂无速度数据
供应商价格排行
供应商价格排行
2 个供应商
最便宜: NVIDIA最贵: DeepInfra
供应商输入输出
1NVIDIA主要
$0
$0
2DeepInfra
$0
$0
比较该模型在不同 API 供应商之间的定价。