DeepScaleR
DeepScaleR is a 1.5-billion-parameter language model fine-tuned from DeepSeek-R1-Distilled-Qwen-1.5B using distributed reinforcement learning and a novel iterative context-lengthening strategy that gradually increases its context window from 8K to 24K tokens during training. It was trained on ~40,000 carefully curated mathematical problems drawn from competition-level datasets like AIME (1984–2023), AMC (pre-2023), Omni-MATH, and STILL. DeepScaleR achieves 43.1% accuracy on AIME 2024, a roughly 14.3 percentage point boost over the base model, and surpasses the performance of the proprietary O1-Preview model despite its much smaller size. It also posts strong results on a suite of math benchmarks (e.g., MATH-500, AMC 2023, Minerva Math, OlympiadBench), demonstrating that small, efficient models tuned with RL can match or exceed larger baselines on reasoning tasks.
Learn more
GLM-4.1V
GLM-4.1V is a vision-language model, providing a powerful, compact multimodal model designed for reasoning and perception across images, text, and documents. The 9-billion-parameter variant (GLM-4.1V-9B-Thinking) is built on the GLM-4-9B foundation and enhanced through a specialized training paradigm using Reinforcement Learning with Curriculum Sampling (RLCS). It supports a 64k-token context window and accepts high-resolution inputs (up to 4K images, any aspect ratio), enabling it to handle complex tasks such as optical character recognition, image captioning, chart and document parsing, video and scene understanding, GUI-agent workflows (e.g., interpreting screenshots, recognizing UI elements), and general vision-language reasoning. In benchmark evaluations at the 10 B-parameter scale, GLM-4.1V-9B-Thinking achieved top performance on 23 of 28 tasks.
Learn more
Hy3
Hy3 preview is Tencent Hy’s most intelligent model in the Hy series to date, built as a 295B-parameter Mixture-of-Experts model with 21B activated parameters, 3.8B MTP layer parameters, and support for up to a 256K token context window. As the first model trained on Tencent Hy’s rebuilt infrastructure, Hy3 preview is designed to improve real-world usability across complex reasoning, instruction following, context learning, coding, agent capabilities, and overall inference performance. It integrates both fast and slow thinking capabilities, allowing direct responses for simpler tasks and deeper reasoning for complex math, coding, and reasoning work. The model is built around well-rounded capabilities across long-context understanding, instruction following, tool use, and agent workflows, with evaluation focused not only on standard benchmarks but also on authentic business and development scenarios.
Learn more
DeepSeek R1
DeepSeek-R1 is an advanced open-source reasoning model developed by DeepSeek, designed to rival OpenAI's Model o1. Accessible via web, app, and API, it excels in complex tasks such as mathematics and coding, demonstrating superior performance on benchmarks like the American Invitational Mathematics Examination (AIME) and MATH. DeepSeek-R1 employs a mixture of experts (MoE) architecture with 671 billion total parameters, activating 37 billion parameters per token, enabling efficient and accurate reasoning capabilities. This model is part of DeepSeek's commitment to advancing artificial general intelligence (AGI) through open-source innovation.
Learn more
