Nex N2 Pro — benchmark results
Nex AGI's open 397B-A17B mixture-of-experts model for coding and agentic workflows. Provider: Nex AGI. Released 2026-06-03. Access: Open.
Unified ELO 1862 ± 27, rank #93 of 1776 rated models, from 47 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SvelteBench | 98.9 | Average pass@1 (%) | 92.2 |
| AA GPQA Diamond | 89.19 | Accuracy (%) | 91.7 |
| AA Humanity's Last Exam | 32.39 | Accuracy (%) | 91.7 |
| Artificial Analysis Intelligence Index | 40.96 | Intelligence Index | 91.5 |
| Wolfram LLM Benchmarking Project | 61.3 | Correct Functionality (%) | 90.7 |
| AA Omniscience - Software Engineering (SWE) - Rust | 74 | Accuracy (%) | 90.2 |
| AA CritPt | 8.57 | Accuracy (%) | 89.7 |
| WildClawBench | 53.5 | Overall Score (self-reported) | 89.5 |
| AA Omniscience - Science, Engineering & Mathematics | 42.4 | Accuracy (%) | 89.2 |
| AA Long Context Reasoning | 67.67 | Accuracy (%) | 88.4 |
| Design Arena (SVG) | 1264 | Elo | 86.9 |
| AA Omniscience - Humanities & Social Sciences | 35.4 | Accuracy (%) | 84.8 |
Interactive version: theaggregate.ai/model?slug=nex-n2-pro · How the rankings work · Data refreshed daily, snapshot 2026-07-22.