Nanbeige4.3-33B open-weights model matches Qwen3.8 27B
A 33B model that runs locally on a laptop yet matches a top ~30B peer on reasoning shifts the practical floor for self-hosted agents, especially for terminal and automation workloads where it beats Qwen3.8 27B decisively. Builders choosing between open-weights models should weigh its higher token consumption and weaker knowledge and coding scores against its abstention behavior. With no confirmed public API, local deployment is currently the main route for users in any region.
Nanbeige, the foundation model team at BOSS Zhipin (Kanzhun Limited), released Nanbeige4.3-33B as an open-weights dense reasoning model under Apache 2.0. The 33B model scores 20 on the Artificial Analysis Intelligence Index v5, equal to Qwen3.8 27B (xhigh), and offers a 524K-token context window with text-only input and output. It leads Qwen3.8 27B on terminal use and automation, scoring 30% on Terminal-Bench 4.0 versus 6%, but trails on coding and knowledge benchmarks such as FrontierCode 2.0 (11% vs 15%) and HLE-Diamond (7% vs 15%). It shows lower hallucination on AA-Omniscience v1.1 (18% vs 29%), declining 71% of questions, and consumes about 44% more output tokens per task (158K vs 110K).
Nanbeige has released Nanbeige4.3-33B, an open weights model matching Qwen3.8 27B (xhigh) at 20 on the Artificial Analysis Intelligence Index v5 with stronger terminal use but weaker knowledge
@Nanbeige is the foundation model research team at BOSS Zhipin, the Chinese recruitment platform operated by Kanzhun Limited. Its dense 33B reasoning model is open weights under Apache 2.0, with text input and output only, a 524K-token context window, and is small enough to run locally on a laptop.
Key results:
➤ Competitive results at ~30B total parameters. Nanbeige4.3-33B and Qwen3.8 27B (xhigh) both score 20, compared with 6 for Muse Glimmer (high, 30B).
➤ Terminal use and physics reasoning are relative strengths. Nanbeige scores 30% on Terminal-Bench 4.0 and 16% on CritPt v2's Hard Subset, vs. 6% and 4% respectively for Qwen3.8 27B.
➤ Different strengths to Qwen3.8 27B despite the same overall score. Nanbeige beats Qwen3.8 27B on AutomationBench-AA (53% vs. 48%), but trails on AA-Briefcase v1.1 (1162 vs. 1391 Elo), FrontierCode 2.0 (11% vs. 15%) and HLE-Diamond (7% vs. 15%).
➤ High abstention and low hallucination rates on Omniscience. Nanbeige scores -4 on AA-Omniscience v1.1 vs. -6 for Qwen3.8 27B, with a hallucination rate of 18% vs. 29%. It answers fewer questions correctly (12% vs. 17%) and declines 71% of questions.
➤ Similar intelligence with more output tokens per task. Nanbeige used 158K output tokens per Intelligence Index task vs. 110K for Qwen3.8 27B, about 44% more.
Additional model details:
➤ Type: Open weights reasoning (Apache 2.0 license)
➤ Size: 33B total parameters (dense)
➤ Modalities: Text input and output only
➤ Context window: 524K
➤ API availability: No confirmed public first- or third-party APIs
