Recently, LMSYS Organization's Large Model Arena (Chatbot Arena) released its latest rankings update. LMSYS Chatbot Arena's top-ranked model has surpassed all open-source models, including Llama3-70B, Qwen2-72B, Nemotron-4-340B, Gemma2-27B, and others, earning the prestigious title of the global leader among open-source models.
Compared to the 0507 open-source Chat version, DeepSeek-V2-0628 has shown comprehensive improvements in areas such as code and mathematical reasoning, instruction following, role-playing, and JSON Output.
Chatbot Arena is a globally recognized authoritative platform for large model blind testing, employing a manual blind testing method to ensure the fairness of evaluations. In this round of assessments, DeepSeek-V2-0628 demonstrated world-class capabilities in solving complex problems, including hard prompts, code, longer queries, and mathematics, on par with top models like GPT-4-Turbo-0409 and Claude3Opus.
DeepSeek-V2-0628 not only excels on the international stage but also ranks highly in domestic model evaluations, standing second among all domestic models, showcasing its strong competitive edge. Additionally, DeepSeek-V2-0628 was launched on June 28, 2024, offering API and web-based services at highly competitive prices.
Model download link: https://top.aibase.com/tool/deepseek-v2-chat-0628
Key highlights:
🏆 Global Leadership: DeepSeek-V2-0628 tops the global open-source models, affirming its leading position in the AI field.
🔍 Problem-Solving Capability: DeepSeek-V2-0628 exhibits world-class abilities in tackling complex problems and coding challenges.
💼 Competitive Pricing: DeepSeek-V2-0628's API and web services are available at highly competitive prices, offering value to the market.
