RULER
Synthetic long-context tests
long context
Definition
- Version
- not in the notes
- Category
- long context
- Maintainer
- NVIDIA
- Status
- not in the notes
- Home page
- not in the notes
Sources
- huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
| Nemotron 3 Ultra 550B A55B | 94.7 % | vendor-reported | at 1M context | – | – | huggingface.co |
 A.X K2 | 94.6 % | vendor-reported | Thinking mode; Overall average | A.X K2 model card | Jul 2026 | huggingface.co |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "RULER", https://aurion.semai.id/benchmarks/ruler/, records of October 2026.