Nanbeige 发布 Nanbeige4.3-33B 开源推理模型
BOSS 直聘的团队开源了个 33B 推理模型，终端操作能力比 Qwen3.8 强不少，笔记本就能跑，还允许商用。
Nanbeige（BOSS 直聘旗下基础模型团队）发布 Nanbeige4.3-33B，采用 Apache 2.0 开源。该模型在 Artificial Analysis Intelligence Index v5 上得 20 分，与 Qwen3.8 27B（xhigh）持平。它是稠密 33B 架构，上下文窗口 524K，仅支持文本输入输出，可在笔记本上本地运行。在 Terminal-Bench 4.0 上得 30%，高于 Qwen3.8 27B 的 6%，但 FrontierCode 2.0 上 11% 低于对手的 15%。幻觉率 18% 低于 Qwen3.8 27B 的 29%，代价是拒绝回答 71% 的问题，且每个任务消耗 158K 输出 token，比 Qwen3.8 27B 多约 44%。
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
