Nemotron 3 Super — Benchmarks, Capabilities, and Use Cases
Nemotron 3 Super is a open-weight AI model from NVIDIA (12B/120B MoE), classified as Advanced tier with a 1M tokens context window. It is available directly in ...
4 min read
Nemotron 3 Ultra is a top-tier frontier AI model, developed by NVIDIA and released in June 2026. As an open-weight model, its trained weights are publicly available — you can self-host it, fine-tune it on proprietary data, or run it on-premise without API dependencies. It supports a 262K-token context window, adequate for most documents and multi-turn applications.
On the FlowHunt AI Leaderboard it is one of 24 tracked models, evaluated across 2 benchmarks. Standout scores: 48.0 pts on AA Intelligence Index (#7 of 9); 86.7% on GPQA Diamond (#9 of 14).
Nemotron 3 Ultra was released on June 4, 2026 as NVIDIA’s top open-weight language model, designed for deployment on Blackwell-generation GPU clusters (B200, GB200 NVLink). At 55B active parameters from a 550B total MoE pool, Ultra was built to maximise accuracy on NVIDIA hardware using TensorRT-LLM’s Blackwell-specific optimisations. At launch it held the highest Artificial Analysis Intelligence Index score of any fully open-weight model — making it the benchmark reference for enterprise customers investing in NVIDIA’s Blackwell infrastructure who wanted an included, inference-optimised model alongside their hardware purchase.
Note: Highest-intelligence US open-weight model. Optimised for NVIDIA Blackwell.
- Released
- June 2026
- Parameters
- 55B/550B MoE
- Context
- 262K tokens
- Weights
- Open
- Tier
- Frontier
- Provider
- NVIDIA
Nemotron 3 Ultra Benchmark Rankings
Rank among all 24 models tracked on this leaderboard. SR = self-reported · 3P / AA / C = independently verified.
| Benchmark | Score | Rank | Source | What it measures |
|---|---|---|---|---|
| GPQA Diamond | 86.7% | 9 of 14 | SR | Graduate-level Google-proof science Q&A |
| AA Intelligence Index | 48.0 pts | 7 of 9 | AA | Artificial Analysis composite score (independent) |
Detailed Benchmark Scores
GPQA ◇
SR
86.7%
Graduate-level Google-proof science Q&A
AA Idx
AA
48.0 pts
Artificial Analysis composite score (independent)
Nemotron 3 Ultra vs. Frontier Peers
Head-to-head benchmark comparison with other Frontier-tier models. Higher is better for all metrics.
| Benchmark | Nemotron 3 Ultra | Claude Opus 4.8 | Claude Opus 4.7 |
|---|---|---|---|
| GPQA ◇ | 86.7% | 93.6% | 94.2% |
| AA Idx | 48.0 pts | 61.4 pts | 57.3 pts |
About NVIDIA
NVIDIA Corporation designs and sells graphics processing units (GPUs) and system-on-chip units that have become the dominant hardware platform for AI model training and inference globally, with an estimated 80-to-95-percent market share in datacentre AI accelerators. Founded in 1993 by Jensen Huang, Chris Malachowsky, and Curtis Priem, NVIDIA has expanded from its original gaming-graphics focus into a full-stack AI computing company. Its Nemotron model family reflects a vertical integration strategy: by releasing open-weight models optimised specifically for NVIDIA hardware, the company aims to demonstrate the value of its Blackwell-generation GPU clusters while shaping the open-weight ecosystem around NVIDIA-optimised software stacks.
Use Cases
What to Use Nemotron 3 Ultra For
- Scientific & Technical Reasoning
Nemotron 3 Ultra scores 86% on GPQA Diamond (#9 of 14 models), around or above the human PhD-expert baseline. It handles demanding scientific reasoning, research literature summarisation, and knowledge-intensive tasks across STEM disciplines.
- Self-Hosted & Private Deployments
Nemotron 3 Ultra is open-weight (55B/550B MoE parameters) — its trained weights are publicly available for download and self-deployment. Run it on your own GPU hardware or private cloud to ensure data never leaves your environment, eliminate per-token API costs at scale, or fine-tune the model on proprietary datasets.
Strengths & Limitations
Strengths
- Advanced scientific Q&A — 86% GPQA Diamond
- Self-hosted & data-private deployments (open-weight)
- Long-context tasks (262K context window)
Browse the Full AI Model Leaderboard
Compare all 24 models across 11 benchmarks — sortable, sourced, and updated June 2026.
Frequently asked questions
Learn more
MiniMax M3 — Benchmarks, Capabilities, and Use Cases
MiniMax M3 is a open-weight AI model from MiniMax (MoE (undisclosed)), classified as Frontier tier with a 1M tokens context window. It is available directly in ...
4 min read
Mistral Large 3 — Benchmarks, Capabilities, and Use Cases
Mistral Large 3 is a open-weight AI model from Mistral (41B/675B MoE), classified as Advanced tier with a 256K tokens context window. It is available directly i...
4 min read