Language Open Weights
- Params
- 550B
- Context
- 1M
- Released
- Jun 2026
NVIDIA's flagship 550B-A55B open model with 1M context and Mamba-Attention MoE architecture..
Full NVIDIA Nemotron 3 Ultra specs →
🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// COMPARISON
NVIDIA Nemotron 3 Ultra
A head-to-head benchmark comparison of NVIDIA Nemotron 3 Ultra across 8 evaluations.
The models
Benchmark comparison
| Benchmark | NVIDIA Nemotron 3 Ultra |
|---|---|
| agentic | |
| BrowseComp | 44.4% |
| Terminal-Bench 2.1 | 56.4% |
| code | |
| LiveCodeBench | 89% |
| SWE-bench Verified | 70.7% |
| SciCode | 44.6% |
| general | |
| MMLU-Pro | 86.8% |
| MultiChallenge | 63.8% |
| reasoning | |
| Humanity's Last Exam | 26.7% |
Best result per row highlighted in cyan. Each benchmark links to its definition and sources; each model links to its full scorecard.
Frequently asked questions
Which of these models is best for coding? ▶
NVIDIA Nemotron 3 Ultra has the strongest result on LiveCodeBench among the models compared here. See the code-category rows in the table for the full picture.
How many benchmarks are compared? ▶
This comparison covers 8 benchmarks on which at least one of the selected models has a published score.
Where do the benchmark scores come from? ▶
Scores are aggregated from official model cards, technical reports and standard public evaluations, and link back to each benchmark's source. They are updated as new results are published.
Explore further
Build a different comparison
Models (0 selected)
Benchmarks (auto)
Select at least two models.