Nemotron 3 Ultra
Nemotron 3 Ultra from NVIDIA.
Shogo Agent Index
UnrankedNot ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
35
estimated
Long-horizon autonomy
42
estimated
Knowledge-work agents
26
32% measured
Computer use
22
estimated
Security & context learning
35
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 68 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 41 | |
| DeepSWE | est. | 6% | predicted 28 | |
| FrontierSWE | est. | 5% | predicted 5 | |
| CursorBench | est. | 4% | predicted 28 | |
| GSO-Bench | est. | 4% | predicted 11 | |
| METR Time Horizons | est. | 10% | predicted 66 | |
| Vending-Bench 2 | est. | 6% | predicted 17 | |
| PostTrainBench | est. | 4% | predicted 18 | |
| APEX-Agents | 22.7% | 8% | source | |
| GDPval | est. | 7% | predicted 33 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 45 | |
| OSWorld 2.0 | est. | 6% | predicted 3 | |
| OSWorld | est. | 4% | predicted 51 | |
| Cybench | est. | 5% | predicted 53 | |
| CL-bench | est. | 5% | predicted 18 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| CritPt | Reasoning | 3.1% | source |
| DTBench | Knowledge | 90.1% | source |
| FrontierCode | Coding | 13.6% | devin-cli |
| GPQA Diamond | Reasoning | 85.4% | source |
| LMCA | Knowledge | 36.9% | source |
| OTIS Mock AIME | Math | 86.7% | source |
| ProofBench | Math | 2.0% | source |
| SciCode | Coding | 40.3% | source |
| SimpleBench | Reasoning | 41.7% | source |