paper-with-me

홈 › Papers

Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis

2025-02-16 · Kaikai Zhao, Zhaoxiang Liu, Xuejiao Lei, Jiaojiao Zhao, Zhenhong Long, Zipeng Wang, Ning Wang, Meijuan An, Qingliang Meng, Peijun Yang, Minjie Hua, Chaoyang Ma, Wen Liu, Kai Wang, Shiguo Lian

DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations for DeepSeek Series models from the perspective of real-world applications are lacking, making it challenging for users to select the most suitable DeepSeek models for their specific needs. To address this gap, we presents the first comprehensive evaluation of the DeepSeek and its related models (including DeepSeek-V3, DeepSeek-R1, DeepSeek-R1-Distill-Qwen series, DeepSeek-R1-Distill-Llama series, their corresponding 4-bit quantized models, and the reasoning model QwQ-32B) using our enhanced A-Eval benchmark, A-Eval-2.0. Our systematic analysis reveals several key insights: (1) Given identical model architectures and training data, larger parameter models demonstrate superior performance, aligning with the scaling law. However, smaller models may achieve enhanced capabilities when employing optimized training strategies and higher-quality data; (2) Reasoning-enhanced model show significant performance gains in logical reasoning tasks but may underperform in text understanding and generation tasks; (3) As the data difficulty increases, distillation or reasoning enhancements yield higher performance gains for the models. Interestingly, reasoning enhancements can even have a negative impact on simpler problems; (4) Quantization impacts different capabilities unevenly, with significant drop on logical reasoning and minimal impact on text generation. Based on these results and findings, we design an model selection handbook enabling users to select the most cost-effective models without efforts.

📄 PDF Abstract BibTeX arXiv:2502.11164

Code (0)

등록된 구현이 없습니다.

Tasks

Logical ReasoningModel SelectionText Generation

Similar Papers 제목 키워드 기반

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning

2025-05-19 · Qiguang Chen, Libo Qin, Jinhao Liu, Yue Liao 외

Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models (LLMs) on complex tasks, spurring research into its underlying mechanisms. However, two primary challenges remain for real-world ap…

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

2025-01-22 · DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang 외

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary st…

Mathematical ReasoningMulti-task Language UnderstandingQuestion AnsweringReinforcement Learning (RL)

RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability

2025-04-14 · Yichi Zhang, Zihao Zeng, Dongbai Li, Yao Huang 외

Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have been rapidly progressing and achieving breakthrough performance on complex reasoning tasks such as mathematics and coding. However, the open-source R…

Safety Alignment

Information Suppression in Large Language Models: Auditing, Quantifying, and Characterizing Censorship in DeepSeek

2025-06-14 · Peiran Qiu, Siyi Zhou, Emilio Ferrara

This study examines information suppression mechanisms in DeepSeek, an open-source large language model (LLM) developed in China. We propose an auditing framework and use it to analyze the model's responses to 646 politi…

Language ModelingLanguage ModellingLarge Language Model

From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level

2026-01-07 · Jia Li, Yuxin Su, Michael R. Lyu arxiv

As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consistency across massive, real-world, interdependent file systems, has become critic…