NVIDIA
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. It delivers up to 7x higher throughput, providing fast, cost-efficient inference for agentic tasks. Additionally, a long context window gives the model long-term memory, preventing AI agents from losing focus on long, multi-step tasks and ensuring high-accuracy results. Fully open with weights, datasets, and recipes, Super allows easy customization and secure deployment anywhere.
NVIDIA model catalogRank #104 across 526
Rank #123 across 436
Rank #124 across 357
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 36.0 | #104 |
| Artificial Analysis Coding Index | coding | 31.2 | #123 |
| GPQA | reasoning | 80.0% | #115 |
| Humanity's Last Exam | reasoning | 19.2% | #84 |
| SciCode |
| coding, reasoning |
| 36.0% |
| #191 |
| Output Speed | speed | 149.6 tok/s | #76 |
| Time to First Token | speed | 1.06s | #136 |
| Blended Price | cost | $0.412/M | #124 |
| Input Price | cost | $0.300/M | #162 |
| Output Price | cost | $0.750/M | #114 |
| Value Index | cost, overall | 87.4 | #71 |