HomeDoubao-1.5-thinking-pro-250415
N/A
Model parameter quantity
ByteDance
Affiliated organization
Closed Source
License Type
April 17, 2025
Release time
Related figures
Model Introduction
The new deep thinking model Doubao-1.5 performs outstandingly in professional fields such as mathematics, programming, scientific reasoning, and general tasks such as creative writing. It has reached or is close to the industry's top tier level on multiple authoritative benchmarks such as AIME 2024, Codeforces, and GPQA
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.
7.9
Knowledge coverage scope
Possesses core knowledge of mainstream disciplines, but has limited coverage of cutting-edge interdisciplinary fields.
8.8
Reasoning ability
Capable of building multi-level logical frameworks, achieving over 99% accuracy in complex mathematical modeling.
9.1
Model comparison
Doubao-1.5-thinking-pro-250415 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.
Doubao-1.5-thinking-pro-250415 vs Hunyuan-T1-20250822
The deep reasoning model independently developed by Tencent adopts the version number hunyuan-t1-20250822.
Doubao-1.5-thinking-pro-250415 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
Seed-OSS-36B-Instruct
Seed-OSS is an open-source large language model developed by ByteDance's Seed Team, designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features.
Doubao-Seed-1-8-251228
The deep reasoning model released by ByteDance, version 1.8-251228.
Doubao-Seed-1.6-251015 (Thinking)
The deep reasoning model released by ByteDance, which supports manual switching of deep reasoning, and its performance is significantly improved compared to doubao-1.5.
Seed-OSS-36B-Instruct
Seed-OSS is an open-source large language model developed by ByteDance's Seed Team, designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features.
Doubao-Seed-1.6-thinking-250715
The latest version of the seed series model launched by ByteDance, which supports the thinking mode.
Relevant documents
Cursor AI Coding Startup to Hire 200 in Asia-Pacific After Significant Investment from SpaceX
AI coding startup Cursor has unveiled a major global expansion, planning to hire 200 employees across the Asia-Pacific region over the next six months. Key roles include marketing engineers, field engineers, and AI deployment engineers. This move und
Claude Used to Create Malicious npm Packages: Over 670 Compromised Threaten Open Source
A recent cybersecurity incident reveals how large language models (LLMs) are being weaponized for malicious software development. Security researcher Sibi Moosa spotted an attacker using the alias "mousie-5212-super-formatter" leveraging Anthropic's
Reliance unveils $110B AI investment plan as India accelerates tech drive
Mukesh Ambani, the billionaire chairman of India's Reliance conglomerate, announced on Thursday a ₹10 trillion (roughly $110 billion) plan to build AI computing infrastructure across India over the next seven years.Speaking at the India AI Impact Sum
Zhiyuan WITA Ends 'Naked' Robot Interaction with First Compliance Filing
The embodied intelligence sector has reached a significant milestone. According to the latest announcement from the Shanghai Cyberspace Administration, the WITA large model developed by Zhiyuan has successfully completed the filing process, becoming
Anthropic Study Links Polished AI Content to Reduced Human Thinking
When you see AI instantly produce a well-structured, logically clear piece of code or document, are you tempted to trust it without a second thought? According to AIbase, the leading AI company Anthropic recently published a research report titled "A
