NVIDIA
2 ranked models in a catalog of 20 text models. Nemotron 3 Ultra 550B A55B leads this lab at #59 overall.
Ranked models
Global ranks · current snapshot| Rank | Model | SI Score | coding | math | reasoning | preference | Confidence | Blended price | Context | Released |
|---|---|---|---|---|---|---|---|---|---|---|
| #59 | Nemotron 3 Ultra 550B A55BOpen weights | 61.2 | 53.0 | 85.5 | 65.7 | — | 100% | — | 1M | Jun 4, 2026 |
| #116 | Nemotron 3.5 Lightning 30B A3BOpen weights | 46.1 | 38.1 | — | 45.2 | — | 100% | — | 262K | Aug 11, 2026 |
Pillars use a 0–100 scale. * marks an imputed neutral prior where the model has no scored results in that pillar; it is not a measured benchmark result. Prices are USD per 1M tokens; see the blend and price comparison.
Scores and releases
Provisional models
18 awaiting rank-eligible evidence- Nemotron 3.5 Content Safety
No usable open benchmark results found
- Nemotron 3 Nano Omni 30B A3B Reasoning
No usable open benchmark results found
- Nemotron 3 Content Safety
No usable open benchmark results found
- Llama Nemotron Rerank VL 1B v2
No usable open benchmark results found
- Nemotron Cascade 2 30B A3B
No usable open benchmark results found
- Nemotron VoiceChat
No usable open benchmark results found
- Nemotron 3 Super 120B A12B
Results cover 1 pillar; at least 2 required
- Nemotron Content Safety Reasoning 4B
No usable open benchmark results found
- Nemotron 3 Nano 30B A3B
No usable open benchmark results found
- Llama 3.1 Nemotron Safety Guard 8B v3
No usable open benchmark results found
- Nemotron Nano 12B v2 VL
No usable open benchmark results found
- Nemotron Nano 9B v2
No usable open benchmark results found
- Llama 3.3 Nemotron Super 49B v1.5
Results cover 1 pillar; at least 2 required
- Mistral Nemotron
No usable open benchmark results found
- Llama 3.1 Nemotron 70B Instruct
Results cover 1 pillar; at least 2 required
- Llama 3.1 Nemotron Ultra 253B
No usable open benchmark results found
- Llama 3.3 Nemotron Super 49B v1
No usable open benchmark results found
- Nemotron Mini 4B Instruct
No usable open benchmark results found
Latest NVIDIA news
All AI news ↗Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents
Rally Up: ‘Gears of War: E-Day’ Launches on GeForce NOW
NVIDIA, Microsoft Kick Off a New Beginning for Windows PCs With RTX Spark and AI Agents
Why Telecom Operators Are Building Their AI Strategy on Open Models
From Scan to Treatment Plan, AI Helps Close Breast Cancer’s Deadliest Gaps
NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI