Pinxue Guo

Working on agentic VLM/LLM @ Nex-AGI

[Pinxue Guo @PinxueGuo]

@luksamuk @ModelScope2022 @SemiAnalysis_ @ZenMagnets @TeksEdge @0xSero @JulianGoldieSEO @intheworldofai 100% believe you, believe Brazil. Together against to the liar.

[Pinxue Guo @PinxueGuo]

Model merging is all you need?
Don't believe that liars will ever get the last laugh. @ModelScope2022 @SemiAnalysis_ @ZenMagnets @TeksEdge @0xSero @JulianGoldieSEO @intheworldofai
If you want a good model, go explore and train one instead of stealing and deceiving your people

[Nex @NexEcosystem]

The Rio 3.5 model broke the internet this week. The plot twist? It’s essentially our open-source model, Nex N2 Pro, wearing a different hat.

🤯 We analyzed the weights, and the recipe is exact: Rio 3.5 ≈ 0.6 * Nex N2 Pro + 0.4 * Qwen 3.5

It even literally introduces itself as "Nex N2 Pro" if you ask it without initial system prompt!

😂 We are flattered that the City of Rio used our work to achieve SOTA performance. Thanks for the ultimate benchmark validation.

🤝 But in the open-source world, attribution matters.
👇 Full mathematical proof & verify script in the first reply!

[Pinxue Guo @PinxueGuo]

@JeffKazzee @KuittinenPetri @Dr_Singularity Thanks, bro! You’re the voice of truth.

[Pinxue Guo @PinxueGuo]

@JeffKazzee

[Pinxue Guo @PinxueGuo]

@luksamuk @tropidurusbr @juniorro16 @NexEcosystem Thanks, bro! You’re the voice of truth.

[Pinxue Guo @PinxueGuo]

@luksamuk @juniorro16 @NexEcosystem Hhhhhh. Model merging is all you need?

[Pinxue Guo @PinxueGuo]

@SemiAnalysis_

[Pinxue Guo @PinxueGuo]

@cristianmock I guess you won’t anymore

[Pinxue Guo @PinxueGuo]

@CavaliereRio @Prefeitura_Rio Hhhhh really?

[Pinxue Guo @PinxueGuo]

@Zach16976347 @kimmonismus Actually, not finetue. Weight merging is all you need!

[Nex @NexEcosystem]

The first image shows Rio 3.5 admitting it is Nex, and the second image is the result of a model weight similarity check.

[Pinxue Guo @PinxueGuo]

@AnaliseGeopol …

[Pinxue Guo @PinxueGuo]

@JorgeAraujo

[Pinxue Guo @PinxueGuo]

@Tono_Ken3

[Pinxue Guo @PinxueGuo]

I really like this model. Nex-N2!

[Nex @NexEcosystem]

📢 Nex-N2 is here!
A family of agentic models that doesn't just think, it acts!
Coding, search, tool use. All fused into a single agentic reasoning loop.

- Adaptive Thinking, auto-scales reasoning depth per step. Saves ~20% tokens, zero performance loss.
- Coherent Thinking, one thinking paradigm across search, coding, and tool use. No more fragile mode-switching.

🏆 Result: Tier-1 open-source performance on SWE-bench, Terminal-Bench, GDPval, and more, tracking GPT-5.5 and Opus 4.7.

🎉 Open-weight. Try it now.
🔗 https://t.co/7oLSfyOCxB
📦 https://t.co/c2CGhXWaz6
https://t.co/KJYXZIpk8M
https://t.co/vcjdZ9cuB6

[Nex @NexEcosystem]

📢 Nex-N2 is here!
A family of agentic models that doesn't just think, it acts!
Coding, search, tool use. All fused into a single agentic reasoning loop.

- Adaptive Thinking, auto-scales reasoning depth per step. Saves ~20% tokens, zero performance loss.
- Coherent Thinking, one thinking paradigm across search, coding, and tool use. No more fragile mode-switching.

🏆 Result: Tier-1 open-source performance on SWE-bench, Terminal-Bench, GDPval, and more, tracking GPT-5.5 and Opus 4.7.

🎉 Open-weight. Try it now.
🔗 https://t.co/7oLSfyOCxB
📦 https://t.co/c2CGhXWaz6
https://t.co/KJYXZIpk8M
https://t.co/vcjdZ9cuB6

[Dawning Road @TheDawningRoad]

Introduce NexA4A: Automating Agent Construction with Natural Language.

Scaling the next generation of agentic environments:
https://t.co/4JfrZ8by0I
https://t.co/uI5PrZ0ECl

[Dawning Road @TheDawningRoad]

We rebuilt Grouped Per-Token Quantization at the kernel level — removing the real bottleneck in FP8/MoE training and pushing efficiency to the hardware limit:
• 20× faster core ops
• ~2.7 TB/s effective throughput
Details at: https://t.co/vLjipcS6JV

[ModelScope @ModelScope2022]

Meet Nex by NEX-AGI — a non-thinking model built for agents that crushes it in coding, tool use, and roleplay 🚀

✅ SOTA among open models on Tau2-Bench, BFCL V4, GAIA2
✅ Top-tier in frontend, vibe coding, and mini-program/backend dev (human eval confirmed)
✅ Plug-and-play with Claude Code, Cursor, etc.

👉 Expolore Nex: https://t.co/8hhCIoFqRO
🔥 Free for now on SiliconFlow: https://t.co/juqcXci8bz

[Tiezhen WANG @Xianbao_QIAN]

Welcome Nex-N1, a new series of agentic foundational models, to @huggingface

- available in different sizes from 8B, 30B, 32B to 671B
- strong in tool-use, web-search and real-world agentic workflow
- some SFT dataset has been open sourced

Technical report come up soon!