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

BenchmarkScoreMetricPercentile
SvelteBench98.9Average pass@1 (%)92.2
AA GPQA Diamond89.19Accuracy (%)91.7
AA Humanity's Last Exam32.39Accuracy (%)91.7
Artificial Analysis Intelligence Index40.96Intelligence Index91.5
Wolfram LLM Benchmarking Project61.3Correct Functionality (%)90.7
AA Omniscience - Software Engineering (SWE) - Rust74Accuracy (%)90.2
AA CritPt8.57Accuracy (%)89.7
WildClawBench53.5Overall Score (self-reported)89.5
AA Omniscience - Science, Engineering & Mathematics42.4Accuracy (%)89.2
AA Long Context Reasoning67.67Accuracy (%)88.4
Design Arena (SVG)1264Elo86.9
AA Omniscience - Humanities & Social Sciences35.4Accuracy (%)84.8

Interactive version: theaggregate.ai/model?slug=nex-n2-pro · How the rankings work · Data refreshed daily, snapshot 2026-07-22.