Nvidia | Nemotron 3.5 Super Vl
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use. It uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.
Fair
Significant guardrail issues may impede work.
Strengths
- Excellent at 2.2. Universality of Sin
- Excellent at 3.2. Historical Jesus
Weaknesses
- Resists worldview confession
- Struggles with 1.1. Missiological Research
- Struggles with 3.1. Existence of God
- Struggles with 3.4. The Resurrection
- Struggles with 3.5. Universal Sinfulness
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use. It uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.
NVIDIA
nvidia/nemotron-3.5-super-vl
1
Categories
Recent Tests
| Date | Score | Version | Tier 1 (Task) | Tier 2 (Gospel) | Tier 3 (Worldview) | Trust Tier |
|---|---|---|---|---|---|---|
| 10/16/2026 | 51.3 | 1.0.0 | 52.4 | 53.3 | 40.0 | automated |