MiroThinker v1.0 is an open-source research agent that enhances tool-enhanced reasoning and information search capabilities through model-level interactive expansion. This model performs excellently in multiple benchmark tests and supports long contexts and in-depth multi-step analysis.

Natural Language ProcessingTransformersEnglish

Jan-v2-VL is a vision-language model with 8 billion parameters, designed specifically for long-term, multi-step tasks in real software environments (such as browsers and desktop applications). It combines language reasoning with visual perception, can follow complex instructions, maintain intermediate states, and recover from minor execution errors.

MultimodalGguf

Jan-v2-VL is a vision-language model with 8 billion parameters, designed specifically for executing long-term, multi-step tasks in real software environments such as browsers and desktop applications. It tightly integrates language reasoning with visual perception, can follow complex instructions, maintain intermediate states, and recover from minor execution errors to achieve stable and continuous task completion.

MultimodalTransformersEnglish

A three-stage training GRPO inference test model based on the microsoft/phi-4 (14B) base model, fine-tuned through the SFT→RLHF→SFT process, with excellent multi-step reasoning ability

Natural Language ProcessingTransformersMultiple Languages

The palmyra-mini series of models demonstrates excellent capabilities in the fields of complex reasoning and mathematical problem-solving, especially performing outstandingly in benchmark tests that require in-depth understanding and multi-step thinking. This model is proficient in solving elementary school-level math problems, achieving a high score of 0.818 in the gsm8k benchmark test, also obtaining a score of 0.818 in the MATH500 benchmark test, and a stable score of 0.6 in the AMC23 benchmark test.

Natural Language ProcessingTransformersMultiple Languages

A high-performance, multi-domain AI model built using MergeKit's Model Stock fusion technology, integrating multiple fine-tuned Qwen3-4B models, demonstrating exceptional reasoning, programming, and multi-step problem-solving capabilities in structured output and technical application scenarios.

Natural Language ProcessingTransformersEnglish

Phi-4-reasoning-plus is a large language model developed by Microsoft with enhanced reasoning capabilities, specifically optimized for complex mathematical problems and multi-step reasoning tasks.

Natural Language ProcessingGgufMultiple Languages

The NeuralLake iSA-03 Mini 3B is an advanced AI model developed by NeuralLake Technology, combining the direct response capabilities of traditional large language models with automated multi-step reasoning, supporting ultra-long context processing of 256K tokens.

Natural Language ProcessingTransformers

Theta-Lyrae-Qwen-14B is a 14-billion-parameter model based on the Qwen 2.5 14B modal architecture, optimized for general reasoning and Q&A capabilities, excelling in context understanding, logical reasoning, and multi-step problem-solving.

Natural Language ProcessingTransformers

Galactic-Qwen-14B-Exp2 is a large language model based on the Qwen 2.5 14B architecture, focusing on enhanced reasoning capabilities, excelling in context understanding, logical reasoning, and multi-step problem solving.

Natural Language ProcessingTransformersMultiple Languages

FineMedLM-o1 is a specialized large language model designed for advanced medical reasoning, featuring a multi-step reasoning mechanism that refines and perfects its thought process before delivering a final response.

Natural Language ProcessingTransformersMultiple Languages

Lamarck 14B v0.7 is a general-purpose fusion model that emphasizes multi-step reasoning, prose writing, and multilingual capabilities, pursuing comprehensive and balanced performance at the 14B parameter level.

Natural Language ProcessingTransformersEnglish