Nemotron 3 Nano 30B: benchmark results
Provider: NVIDIA. Access: Open.
Unified ELO 1666 ± 39, rank #443 of 2928 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ClaimDB: A Fact Verification Benchmark over Large Structured Data | 0.67 | Accuracy | 72.4 |
| BenchLM | 51.6 | Overall Score | 44.4 |
| Structured Output Benchmark | 84.1 | Overall (%) | 32.1 |
| Wolfram LLM Benchmarking Project | 27.6 | Correct Functionality (%) | 29.4 |
| Sonar LLM Leaderboard - Java - Bug Density | 1.15 | Bugs per 1,000 lines of code (lower is better) | 22 |
| Sonar LLM Leaderboard - Java - Pass Rate | 71.3 | Passing tests (%) | 21.3 |
| SEA-HELM | 46.89 | Mean Score (%) | 19.3 |
| Sonar LLM Leaderboard - Java - Code Smell Density | 22.64 | Code smells per 1,000 lines of code (lower is better) | 18.7 |
| Sonar LLM Leaderboard - Java - Vulnerability Density | 0.39 | Vulnerabilities per 1,000 lines of code (lower is better) | 14.7 |
| Agentic Skills Evaluation Framework | 37.6 | Overall Score w/ (self-reported) | 0 |
Interactive version: theaggregate.ai/model?slug=nemotron-3-nano-30b · How It Works · Data refreshed daily, snapshot 2026-09-23.