Llama 3.3 Nemotron Super 49B v1 (Reasoning) — benchmark results
Llama 3.3 Nemotron Super 49B v1 evaluated with reasoning enabled. Provider: NVIDIA. Released 2025-03-18. Access: Open.
Unified ELO 1493 ± 44, rank #826 of 1776 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA MATH-500 | 95.87 | Accuracy (%) | 81.7 |
| AA MMLU-Pro | 78.46 | Accuracy (%) | 60.5 |
| AA AIME 2025 | 54.67 | Accuracy (%) | 51.1 |
| AA Omniscience - Software Engineering (SWE) - Java | 17 | Accuracy (%) | 51 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 29.09 | Accuracy (%) | 48.9 |
| AA Omniscience - Health | 18.6 | Accuracy (%) | 47.9 |
| AA Omniscience - Software Engineering (SWE) - HTML | 30 | Accuracy (%) | 47.8 |
| AA Humanity's Last Exam | 6.52 | Accuracy (%) | 47.7 |
| AA GPQA Diamond | 64.34 | Accuracy (%) | 43.4 |
| AA Omniscience - Science, Engineering & Mathematics | 24.1 | Accuracy (%) | 41.5 |
| Artificial Analysis Intelligence Index | 12.25 | Intelligence Index | 41.3 |
| AA Omniscience - Business | 14.7 | Accuracy (%) | 39.5 |
Interactive version: theaggregate.ai/model?slug=llama-3-3-nemotron-super-49b-v1-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.