Nemotron 3.5 Super VL 120B A12B

Nemotron 3.5 Super VL 120B A12B is a reasoning model from NVIDIA in the Nemotron 3.5 Super VL family. 20 benchmarks count toward its index, in 6 categories.

  • Open weights
  • Reasoning
  • Input: text
  • Released 2026-10
RankedEnough results for an index.
IndexAll categories, out of 100.51.0±5.1Median 51.0
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.—Median 1422

Run locally

124.45B parameters
16-bit
262.3 GB
8-bit
139.8 GB
4-bit
80.2 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 128 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.5 counted47.8150 / 218
CodingCode writing and repair.5 counted53.0119 / 209
ReasoningLogic problems and puzzles.2 counted56.178 / 227
MultimodalTasks with images and text.4 counted47.470 / 84
KnowledgeFacts and expert knowledge.3 counted52.7116 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted55.2—
MathMath problems.None counted——

Results

20 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
LiveCodeBench v6Coding88.2%13 / 59
Critical Physics TasksReasoning10.9%62 / 214
GPQA Diamond · BenchLMKnowledge89.5%33 / 84
GDPval-AA normalizedAgentic33.1%55 / 133
BrowseCompAgentic78.0%31 / 63
Artificial Analysis SciCodeCoding47.8%61 / 114
CharXiv ReasoningMultimodal80.8%31 / 49
Humanity's Last ExamKnowledge29.2%49 / 77
Instruction Following BenchmarkInstruction70.9%40 / 57
SWE-bench ProCoding51.8%65 / 83
V*Multimodal85.6%12 / 14
MathVisionMultimodal78.2%21 / 24
Vibe Code Bench v1.1Coding3.7% ±1.9111 / 123
BabyVisionMultimodal29.6%10 / 11
Terminal-Bench 4.0Agentic0.0%59 / 61
Tax Agent BenchFinance11.6% ±2.265 / 82
Legal Research BenchLegal10.1% ±2.181 / 90
HLAB-Vals-1.1Legal3.8% ±1.332 / 35
Apex ShortlistMath88.4%—
MMLongBench-DocMultimodal62.8%—

Sources

BenchLMCC BY-NC 4.0Vals AINo licence stated

History

5 releases
Index52.3 → 51.0
23 Oct 202612 Nov 2026

Questions

How good is Nemotron 3.5 Super VL 120B A12B?
Its index is 51.0 out of 100. That is place 142 of 283 ranked models.
What is Nemotron 3.5 Super VL 120B A12B best at?
Reasoning: 56.1 out of 100, place 78 of 227.
What is the context window of Nemotron 3.5 Super VL 120B A12B?
1M tokens.
Is Nemotron 3.5 Super VL 120B A12B open source?
Yes. Its weights are published.
When was Nemotron 3.5 Super VL 120B A12B released?
October 2026.

Badge

Nemotron 3.5 Super VL 120B A12B on Inference360: place 142 of 283, index 51.0
HTML
<a href="https://inference360.ai/models/nemotron-3-5-super-vl-120b-a12b"><img src="https://inference360.ai/badges/nemotron-3-5-super-vl-120b-a12b.svg" alt="Nemotron 3.5 Super VL 120B A12B on Inference360: place 142 of 283, index 51.0" height="20"></a>
Markdown
[![Nemotron 3.5 Super VL 120B A12B on Inference360: place 142 of 283, index 51.0](https://inference360.ai/badges/nemotron-3-5-super-vl-120b-a12b.svg)](https://inference360.ai/models/nemotron-3-5-super-vl-120b-a12b)

Compare with

GPT-5.4 nano50.9Ling 3.0 Flash50.9MiniMax M2.751.2Nemotron 3.5 Super VL 120B A12B NVFP450.8Qwen3.5-27B51.3

More from NVIDIA

All models
Nemotron 3.5 Super VL 120B A12B NVFP450.8Nemotron 3.5 Bolt 74B-A9B46.4Nemotron 3.5 Bolt 74B-A9B BF16UnrankedNemotron 3.5 Super VLUnrankedNemotron 3.5 Bolt E4BUnranked