# Nex-AGI releases open-weight Nex-N2.6 agentic model under Apache 2.0

> Original title: Switch from Claude Code to Codex, Cursor or your own harness, and Nex-N2.6 still calls only the tools that are actually there. The open-w...

- Source: ModelScope
- Published: 2026-11-11T12:07:51.000Z
- Bad Influence: https://badinfluence.news/items/aavd0pc8b6wp2nwun18pxkt2x
- Original: https://x.com/ModelScope2022/status/2120488675314466888

## Summary

ModelScope announces Nex-N2.6, a 321B open-weight multimodal agentic model from Nex-AGI built on GLM-5.3-Flash for computer use, coding and long-horizon tasks. The post reports 100% valid tool selection across 956 contexts, a drop in reasoning repetition from 16.0% to 1.6%, and 83.0 on OSWorld. It offers 256K context via API or self-hosted FP8 weights on SGLang, released under Apache 2.0.

## Why it matters

The post gives benchmark figures for tool selection, reasoning repetition, and OSWorld computer use, showing how the model compares with its GLM-5.3-Flash base and earlier Nex versions.

## Post

Switch from Claude Code to Codex, Cursor or your own harness, and Nex-N2.6 still calls only the tools that are actually there. The open-weight 321B multimodal agentic model from Nex-AGI is built on GLM-5.3-Flash for computer use, coding and long-horizon tasks. 📜 Apache 2.0 🤖 https://www.modelscope.ai/models/nex-agi/Nex-N2.6

🛠️ Harness-agnostic tool use: 100% valid tool selection across 956 real-world contexts, matching GPT-6-Sol and up from 80.56% for Nex-N2.5-Pro.

🔁 Far less looping: reasoning repetition drops 90%, from 16.0% to 1.6%, on 698 real failure cases replayed from the exact point where the previous model stalled. Fewer wasted tokens on long runs.

🖥️ Stronger computer use: 83.0 on OSWorld, 5.0 points above its GLM-5.3-Flash base, while holding 84.1 on Terminal-Bench 2.1.

⚡ Ready to run: 256K context via API, or self-host the FP8 weights on SGLang behind an OpenAI-compatible endpoint with low, high or max reasoning effort.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW18-9vb0AAisKi.jpg&mode=thumb&exp=1794700800&sig=fa8834894e8e03eb)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW19AEPaoAEiWNe.jpg&mode=thumb&exp=1794700800&sig=afdeb0f94f8b0e07)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW19Bxxa8AAW6wx.jpg&mode=thumb&exp=1794700800&sig=d5b561c71f42d2c5)