BOSS Zhipin’s Nanbeige Lab releases open-source Nanbeige4.3-33B for coding and office agents

BOSS Zhipin’s Nanbeige Lab releases open-source Nanbeige4.3-33B for coding and office agents

N
News Editor
2026-10-26 03:57:32
Nanbeige Lab, a research unit under recruitment platform BOSS Zhipin, has released Nanbeige4.3-33B as an open-source model aimed at coding and office agents. The model supports a 512K context window and is distributed under the Apache 2.0 license. According to the official comparison, it was benchmarked against Qwen3.8-27B, Meta Muse Glimmer 30B, and Gemma 4 31B, and ranked first in 17 of 20 disclosed tests. In Terminal-Bench 2.1, Nanbeige4.3-33B scored 80.9 versus Qwen’s 73.0. On DeepSWE, it posted 65.5 compared with 42.5, while its score on the office automation benchmark Automation Bench reached 54.2, above Qwen’s 38.3. Qwen remained ahead on SWE-Bench Pro and GDPval. The lab said it had previously focused on 3B-scale small models. Its earlier Nanbeige4.2-3B improved effective compute depth by reusing Transformer layers without increasing parameter count. This time, the team trained a 33B model first and plans to use it as a teacher model, distilling coding and tool-use capabilities into the upcoming Nanbeige4.3-3B.

Nanbeige Lab, a unit under recruitment platform BOSS Zhipin, has released the open-source model Nanbeige4.3-33B for coding and office agents. The model supports a 512K context window and uses the Apache 2.0 license.

Benchmark results released

The lab compared Nanbeige4.3-33B with Qwen3.8-27B, Meta Muse Glimmer 30B, and Gemma 4 31B. In the 20 published tests, the model ranked first in 17.

Its Terminal-Bench 2.1 score came in at 80.9, above Qwen’s 73.0. On DeepSWE, it reached 65.5, compared with 42.5. In the office automation test Automation Bench, it scored 54.2, higher than Qwen’s 38.3. Qwen still led on SWE-Bench Pro and GDPval.

Next step for the model line

Nanbeige Lab had previously focused mainly on 3B-scale small models. The previous-generation Nanbeige4.2-3B increased effective compute depth by reusing Transformer layers without adding parameters.

This time, the team trained a 33B model first and plans to use it as a teacher model, then distill coding and tool-calling capabilities into the upcoming Nanbeige4.3-3B.

This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan.
1700

Disclaimer:

The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.

Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.