OpenThinker - Agent - v1 is an open - source intelligent agent model that is subsequently trained based on Qwen3 - 8B. It is designed for terminal operations and software engineering tasks. It is first trained on a high - quality supervised fine - tuning dataset and then further optimized through reinforcement learning. It performs excellently in agent benchmark tests such as Terminal - Bench 2.0 and SWE - Bench.

Natural Language ProcessingTransformersOther

Fyodor-Q3-8B-Instruct is a high-fidelity instruction-tuned model designed for intelligent reasoning and robust code generation. It is based on the Qwen3-8B architecture and trained with a high-rank LoRA configuration. It excels in planning before coding and is well-suited for complex software engineering tasks.

Natural Language ProcessingTransformersMultiple Languages

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

This model is a professional code generation model fine-tuned on the swe_only_sweagent dataset based on Qwen2.5-Coder-32B-Instruct. It achieved a loss value of 0.1210 on the evaluation set and is specifically optimized for software engineering-related tasks.

Natural Language ProcessingTransformers

KAT-Dev-72B-Exp is an open-source large language model with 72 billion parameters for software engineering tasks, achieving an accuracy of 74.6% in the SWE-Bench Verified benchmark test. It is an experimental reinforcement learning version of the KAT-Coder model.

Natural Language ProcessingTransformers

This is a binary classification model for software requirements based on BERT fine-tuning, specifically designed to identify and classify requirements and non-requirement texts in software requirement documents, accurately distinguishing functional requirement descriptions from other content.

Natural Language ProcessingSafetensorsEnglish

This is a vulnerability classification model fine-tuned based on RoBERTa-base, specifically designed for the CWE (Common Weakness Enumeration) parent vulnerability classification task. It achieved an accuracy of 87.5% and an F1 macro value of 0.6248 on the evaluation set, providing effective support for software security vulnerability analysis.

Natural Language ProcessingTransformers

SWE-agent-LM-7B is an open-source language model specifically designed for the software engineering field. It is fine-tuned based on Qwen2.5-Coder-7B-Instruct. This model can effectively solve software engineering-related problems and provide intelligent support for developers, which has important practical value.

Natural Language ProcessingTransformersEnglish

Devstral is a large language model specifically designed for software engineering tasks, developed in collaboration by Mistral AI and All Hands AI. It excels in code exploration, multi-file editing, and tool invocation.

Natural Language ProcessingSafetensorsMultiple Languages

A software engineering-specific model based on Qwen/Qwen2.5-Coder-32B-Instruct, using an innovative quantization method to improve accuracy

Natural Language ProcessingTransformers

Devstral Small 1.1 GGUF is a large language model specifically designed for software engineering tasks. It combines the technical advantages of Mistral AI and All Hands AI and performs excellently in code processing and software engineering agency.

Natural Language ProcessingGgufEnglish

Devstral Small 1.1 is a large language model optimized for software engineering tasks, developed in collaboration by Mistral AI and All Hands AI, supporting multiple languages and tool invocation.

Natural Language ProcessingSafetensorsMultiple Languages

Devstral 1.1 is an intelligent large language model jointly developed by Mistral AI and All Hands AI, specifically designed for software engineering tasks. This model performs excellently in the SWE-bench benchmark test, ranking first among open-source models. It has 24 billion parameters and a long context window of 128k tokens.

Natural Language ProcessingSafetensorsMultiple Languages

Devstral 1.1 is a large language model designed specifically for software engineering tasks, supporting tool calls and visual functions, suitable for codebase exploration and multi-file editing.

Natural Language ProcessingGgufMultiple Languages

Devstral is a large language model specifically designed for software engineering tasks, developed in collaboration by Mistral AI and All Hands AI. It performs excellently in the SWE-bench benchmark test and is the top-ranked open-source model.

Natural Language ProcessingSafetensorsMultiple Languages

Devstral is an intelligent large language model specifically designed for software engineering tasks, developed in collaboration by Mistral AI and All Hands AI.

Natural Language ProcessingGgufMultiple Languages

Devstral is an intelligent large language model specifically designed for software engineering tasks, developed in collaboration by Mistral AI and All Hands AI. It excels at using tools to explore code repositories, edit multiple files, and provides strong support for software engineering agents.

Natural Language ProcessingSafetensorsMultiple Languages

A text generation model based on the Transformer architecture, focusing on software engineering tasks and supporting a context length of 40k tokens.

Natural Language ProcessingGgufEnglish

DeepSWE-Preview is a fully open-source and advanced coding intelligent agent, trained through reinforcement learning, and performs excellently in software engineering tasks.

Natural Language ProcessingTransformersEnglish