# Complex Problem Solving

DeepSeek-R1-Llama-8B-F32-GGUF is the quantized version of DeepSeek-R1-Distill-Llama-8B, trained directly with reinforcement learning, featuring capabilities such as self-verification, reflection, and generating extended chain-of-thought reasoning.

Skywork-R1V2-38B is currently the most advanced open-source multimodal reasoning model, demonstrating outstanding performance in multiple benchmark tests with robust visual reasoning and text comprehension capabilities.

ReasonFlux-F1-7B is a hierarchical large language model reasoning model based on thinking template expansion, fine-tuned through template-enhanced reasoning trajectories, demonstrating outstanding performance in multiple reasoning tasks.

OpenVLThinker-7B is a vision-language reasoning model specifically designed for multimodal tasks, with particular optimization for solving visual mathematical problems.

A standardized denoising Fourier interpolation hybrid model based on the Qwen series, renowned for high-quality responses and emotional resonance as a thinking-oriented large language model

A model trained through reinforcement fine-tuning based on Qwen 2.5 32B Instruct, specifically designed to solve challenging deductive reasoning problems in the Temporal Clue dataset.

A mathematical reasoning model fine-tuned based on Mistral-Small-24B-Instruct-2501, optimized for mathematical reasoning capabilities

A 7B-parameter model in the Skywork o1 open model series, trained on Qwen2.5-Math-7B-Instruct, featuring enhanced reasoning capabilities through progressive process rewards

Tülu3 is a new generation of instruction-following model family developed by the Allen Institute for Artificial Intelligence, excelling in standard chat applications and complex problem-solving.

HK-O1aw is a legal assistant with O1-style complex reasoning capabilities, based on LLaMA-3.1-8B, specifically designed for the legal domain in Hong Kong.

A supervised fine-tuned model based on Smaug-34B, focused on enhancing mathematical and reasoning capabilities, excelling among 34B-scale models.

BoreanGale-70B is a 70B-parameter large language model merged using a custom algorithm (NearSwap), combining the miqu-1-70b-sf and WinterGoddess-1.4x-70B-L2 models.