HomeNanbeige3.5-Pro-Thinking
N/A
Model parameter quantity
Nanbeige
Affiliated organization
Closed Source
License Type
October 23, 2025
Release time
Model Introduction
Nanbeige3.5-Pro-Thinking is a reasoning-enhanced version of the self-developed Nanbeige series by BOSS Zhipin, designed for both general and recruitment-specific scenarios.
Comprehensive score
Language dialogue
Knowledge reserve
Reasoning association
Mathematical calculation
Code writing
Command following
Swipe left and right to view more
Language comprehension ability
Capable of understanding complex contexts and generating logically coherent sentences, though occasionally off in tone control.
8.2
Knowledge coverage scope
Possesses core knowledge of mainstream disciplines, but has limited coverage of cutting-edge interdisciplinary fields.
8.4
Reasoning ability
Unable to maintain coherent reasoning chains, often causing inverted causality or miscalculations.
6.1
Model comparison
Nanbeige3.5-Pro-Thinking vs Qwen2.5-7B-Instruct
Like Qwen2, the Qwen2.5 language models support up to 128K tokens and can generate up to 8K tokens. They also maintain multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
Nanbeige3.5-Pro-Thinking vs Hunyuan-T1-20250822
The deep reasoning model independently developed by Tencent adopts the version number hunyuan-t1-20250822.
Nanbeige3.5-Pro-Thinking vs Spark-X1
The inference model Spark X1 released by iFlytek, on the basis of leading domestic mathematical tasks, benchmarks the performance of general tasks such as inference, text generation, and language understanding against OpenAI o1 and DeepSeek R1.
Related model
Nanbeige2-16B-Chat
The Nanbeige2-8B-Chat is the latest 8B model developed by the Nanbeige Lab
Nanbeige2-8B-Chat
The Nanbeige2-16B-Chat is the latest 16B model developed by the Nanbeige Lab
Nanbeige2-16B-Chat
The Nanbeige2-8B-Chat is the latest 8B model developed by the Nanbeige Lab
Qwen2.5-7B-Instruct
Like Qwen2, the Qwen2.5 language models support up to 128K tokens and can generate up to 8K tokens. They also maintain multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
Hunyuan-T1-20250822
The deep reasoning model independently developed by Tencent adopts the version number hunyuan-t1-20250822.
Relevant documents
Anthropic's experimental AI Claude completes negotiations and transactions in e-commerce test
As artificial intelligence advances rapidly, Anthropic quietly rolled out an internal experiment called "Project Deal" last Friday, showcasing AI's potential in e-commerce. The experiment had its AI model Claude autonomously handle buying, selling, a
DeepSeek Code poised for launch
As AI technology accelerates, DeepSeek is at a thrilling juncture. The AI company recently revealed it has secured over 70 billion yuan in funding. Leadership has emphasized a commitment to groundbreaking AI research over immediate commercial gains.
Musk’s Grok: 1.5 Trillion Parameters and Cursor Code Absorption—Game Changer or Bluff?
Elon Musk is finally making a move.In the AI programming race, OpenAI and Anthropic are accelerating, while xAI appears to be lagging. Musk has often stated his aim to rival Claude, yet despite multiple updates to the Grok4.X series, the results look
OpenAI Secretly Changes Charter to Make Removing Altman Harder
Following the 2023 coup-like incident, OpenAI has further solidified protections for CEO Sam Altman by updating its corporate bylaws. Recently released court documents reveal that Altman's position is now rock-solid, with substantially higher barrier
Meta AI now responds to buyer messages on Facebook Marketplace
Facebook Marketplace introduces new Meta AI features, including automated replies to buyer inquiries, the company announced Thursday. The platform also leverages AI to accelerate item listings, summarize seller profiles, and now lets sellers offer sh
