# Nanbeige4.3-33B releases with 512K context and agentic benchmark results

> Original title: Nanbeige4.3-33B is here with 512K context and strong agentic performance in a 33B dense model.

- Source: ModelScope
- Published: 2026-10-26T06:01:50.000Z
- Bad Influence: https://badinfluence.news/items/accpp8yjigt674htfuhguxw8q
- Original: https://x.com/ModelScope2022/status/2114598356060131437

## Summary

ModelScope announces Nanbeige4.3-33B, a 33B dense model with 512K context, and says it leads most benchmarks against Qwen3.8-27B, Muse-Glimmer-30B, and Gemma4-31B. It reports 80.9 on Terminal-Bench 2.1 and 65.5 on DeepSWE, versus 73.0 and 42.5 for Qwen3.8-27B. The model is licensed under Apache 2.0, supports Transformers, SGLang, and vLLM, and is planned as a teacher model for distillation into smaller models.

## Post

Nanbeige4.3-33B is here with 512K context and strong agentic performance in a 33B dense model.
🤖 https://modelscope.ai/models/nanbeige/Nanbeige4.3-33B

🏆 SOTA agentic performance at the 30B scale: Nanbeige4.3-33B leads most benchmarks in the team’s comparison with open models including Qwen3.8-27B, Muse-Glimmer-30B, and Gemma4-31B.
💻 Agentic coding: Scores 80.9 on Terminal-Bench 2.1 and 65.5 on DeepSWE, compared with 73.0 and 42.5 for Qwen3.8-27B.
🧰 Professional workflows: Reaches 54.2 on Automation Bench and 44.8 on JobBench, covering tasks across tools, occupations, and industries.
🧠 Flexible reasoning and tool use: Switch between thinking and non-thinking modes, and retain previous reasoning for multi-turn agent workflows.
🔬 A teacher for smaller agents: Nanbeige4.3-33B is the flagship teacher model for the team’s planned distillation into smaller models.
📜 Apache 2.0. Supports Transformers, SGLang, and vLLM.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHViP_70W0AELn36.jpg&mode=thumb&exp=1793491200&sig=32f39b8f77bd383c)