Nemotron 3.5 Super VL (120B A12B)
MultimodalNemotron 3.5 Super VL is NVIDIA's open 120B total / 12B active multimodal mixture-of-experts model, pairing a hybrid Mamba-2 and attention backbone with a C-RADIO vision encoder. It accepts text, image and video input, supports up to 1M context, tool use and configurable reasoning, and targets long-running agents. Released 2026-10-15 under OpenMDW-1.1; DeepInfra serves it at $0.20/$1.00 per million tokens.
Key Specifications
Parameters
120.0B
Context
262.1K
Release Date
October 15, 2026
Average Score
60.9%
Timeline
Key dates in the model's history
Announcement
October 15, 2026
Last Update
October 20, 2026
Today
October 27, 2026
Technical Specifications
Parameters
120.0B
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Pricing & Availability
Input (per 1M tokens)
$0.20
Output (per 1M tokens)
$1.00
Max Input Tokens
262.1K
Max Output Tokens
262.1K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning
Benchmark Results
Model performance metrics across various tests and benchmarks
Programming
Programming skills tests
SWE-Bench Verified
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
Reasoning
Logical reasoning and analysis
GPQA
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; GPQA-Diamond • Self-reported
Other Tests
Specialized benchmarks
AA-LCR
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; AA-LCR v1.1 • Self-reported
BrowseComp
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
CharXiv-R
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; CharXiv reasoning • Self-reported
GDPval-AA
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; GDPval-AA v2 Elo (max_score 3000) • Self-reported
Humanity's Last Exam
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; HLE text-only • Self-reported
IFBench
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
LiveCodeBench v6
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; LiveCodeBench v6 • Self-reported
MathVision
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
MMLongBench-Doc
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
OCRBench-V2 (en)
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; OCRBench v2 EN • Self-reported
OmniScience
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; AA-Omniscience accuracy • Self-reported
OSWorld-Verified
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
SciCode
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; SciCode subtask • Self-reported
SWE-bench Multilingual
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
SWE-Bench Pro
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
Tau3 Banking
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card; τ³-bench (Banking) • Self-reported
Terminal-Bench 2.1
NeMo Gym / NeMo Evaluator; BF16 SuperGA as on HF card • Self-reported
License & Metadata
License
openmdw
Announcement Date
October 15, 2026
Last Updated
October 20, 2026
Compare Nemotron 3.5 Super VL (120B A12B)
All comparisonsSimilar Models
All ModelsNemotron 3.5 Bolt (74B A9B 24GB)
NVIDIA
MM74.0B
Best score:0.9 (GPQA)
Released:Oct 2026
Nemotron 3 Ultra (550B A55B)
NVIDIA
550.0B
Best score:0.9 (GPQA)
Released:Jun 2026
Step-3.5-Flash
StepFun
MM196.0B
Best score:0.9 (TAU)
Released:Feb 2026
Price:$0.10/1M tokens
Kimi K2.6
Moonshot AI
MM1.0T
Best score:0.9 (GPQA)
Released:Apr 2026
Price:$1.20/1M tokens
Kimi K2.5
Moonshot AI
MM1.0T
Best score:0.9 (GPQA)
Released:Jan 2026
Kimi K3
Moonshot AI
MM2.8T
Best score:0.9 (GPQA)
Released:Jul 2026
Price:$3.00/1M tokens
Command A+
Cohere
MM218.0B
Best score:0.8 (TAU)
Released:May 2026
Qwen3.8 Flash Next
Alibaba
MM180.0B
Best score:0.9 (GPQA)
Released:Aug 2026
Price:$0.16/1M tokens
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.