BOSS Zhipin's Nanbeige releases open-weights 33B model, ties Qwen3.8 27B at 20
ArtificialAnlys · x · 2026-11-06
Nanbeige, the foundation model team at Chinese recruitment platform BOSS Zhipin (Kanzhun), has released Nanbeige4.3-33B: an open-weights (Apache 2.0) dense reasoning model scoring 20 on the Artificial Analysis Intelligence Index v5, tying Qwen3.8 27B (xhigh) with stronger terminal use but weaker knowledge, and setting a new Pareto optimal point for Intelligence Index vs. total parameters. For comparison, DeepSeek V4.1 Flash 1017 (max) scores 33 with 552B total parameters but activates only 16B per token via MoE.
Related event: BOSS Zhipin's Nanbeige Releases Open-Source 33B Model(2 posts)→
More from Models
- Grok apologizes for unexpected Cursor charge as users question AI billing reliability — alexcovo_eth · 2026-11-06
- 39 LLMs tested on Rubik's cubes with no tools: only 2 solve a 20-move scramble — JeremyCMorgan · 2026-11-06
- Ampersand Claims 92.2% on SWE-bench Pro HARD-51 at 70% Lower Cost — niloofar_mire · 2026-11-06
- LiteParse Integrates 1.3B MiniCPM-OCR, Beating Gemini Flash on ParseBench — llama_index · 2026-11-06
- GPT-6 meme: Astra does 40% less work when tasks are framed as safety research — repligate · 2026-11-06
- METR chart shows AI benchmark progress nearly doubled, Anthropic Model 4 hits 178.6 AECI — scaling01 · 2026-11-06