BOSS直聘旗下南北阁发布 Nanbeige4.3-33B 开源推理模型
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 t
BOSS直聘旗下基础模型团队南北阁发布 Nanbeige4.3-33B，采用 Apache 2.0 开源协议，33B 稠密参数、仅文本输入输出、524K token 上下文窗口，小到可在笔记本本地运行。该模型在 Artificial Analysis Intelligence Index v5 上得分 20，与 Qwen3.8 27B（xhigh）持平，Terminal-Bench 4.0 得 30%、CritPt v2 Hard Subset 得 16%，均高于后者的 6% 和 4%。但它在 AA-Briefcase v1.1（1162 对 1391 Elo）、FrontierCode 2.0（11% 对 15%）和 HLE-Diamond（7% 对 15%）上落后，且每个任务输出 token 约 158K，比 Qwen3.8 27B 的 110K 多约 44%；目前尚无确认的公开 API。
正文
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