Nanbeige LLM Lab
2 models across 1 family · Latest: Nanbeige4.1-3B (2026-02)
Massive multilingual model, open-source focus.
Nanbeige LLM Lab's portfolio covers 2 active models across 1 current family, spanning rag, agents, and long context. Open a model detail page to compare provider routes and sourced benchmarks.
Covers 4 workload areas across 2 active tracked models; last verified 2026-05-19.
Use it for
- Teams evaluating rag, agents, and long context across this lab's releases
- Comparing model families before committing to a flagship
- Migration and pricing follow-ups across 2 tracked models
Do not use it for
- Choosing a hosting provider without opening a model page for price ladders
Active models
2
Current models from this lab, excluding deprecated ones
Active families
1
Current model families from this lab
Open catalog
2 open
0 open source / 2 open weights
Lowest output price
Not tracked
No provider output pricing linked yet
Latest dated release
2026-02-11
Nanbeige4.1-3B
Freshness
2026-05-19
Researched 106d ago
Information
Release cadence
- Dated releases
- 2
- Latest model
- Nanbeige4.1-3B
- Latest date
- 2026-02-11
Where this lab wins
- RAG: 1 tracked model with ruler / needle retrieval benchmarks.
- Agentic: 1 tracked model with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 1 tracked model with context-token or InfiniteBench-class signal.
- JSON/tool-use: 1 tracked model with BFCL / Nexus strict-JSON routing coverage.
Flagship quality / price signal
- Flagship
- Nanbeige4-3B
- Selection source
- Best sourced coding Q/$
- Coding grade
- unknown
- Benchmark / output price
- Not enough sourced benchmark and price coverage
About
Nanbeige LLM Lab is the AI research team at BOSS Zhipin (Kanzhun Limited), Beijing’s leading online recruitment platform, known for its commitment to open-sourcing powerful multilingual large language models. Despite being a relatively new entrant in this field, the lab has swiftly established itself as a notable open-source contributor through GitHub and Hugging Face. A focal point of the lab’s innovation is the Nanbeige-16B model, a 16-billion parameter LLM trained on an extensive dataset encompassing 2.5 trillion tokens drawn from internet corpora, books, and code.
Featured models
| Model | Released | Context | Input price ($/1M) | Output price ($/1M) | License | Openness |
|---|---|---|---|---|---|---|
| Nanbeige4.1-3B | 2026-02-11 | 256k | - | - | Open Weights | Open weights |
| Nanbeige4-3B | 2025-12-13 | 64k | - | - | Open Weights | Open weights |
Model families
Recent releases
- Nanbeige4.1-3B- 2026-02-11
- Nanbeige4-3B- 2025-12-13
Explore related pages
Last reviewed: 2026-05-19. Data sourced from public lab announcements and provider documentation.