Chatbot Arena

This leaderboard is based on the following benchmarks. Chatbot Arena - a crowdsourced, randomized battle platform for large language models (LLMs). We use 2.8M+ user votes to compute Elo ratings. MMLU - a test to measure a model’s multitask accuracy on 57 tasks. Arena-Hard-Auto - an automatic evaluation tool for instruction-tuned LLMs.

Qwen2.5-Omni

We release Qwen2.5-Omni, the new flagship end-to-end multimodal model in the Qwen series. Designed for comprehensive multimodal perception, it seamlessly processes diverse inputs including text, images, audio, and video, while delivering real-time streaming responses through both text generation and natural speech synthesis. Please check out the video below for more information 😃

QwQ

QwQ is the reasoning-specialized model within the Qwen series. Unlike traditional instruction-tuned models, QwQ leverages advanced reasoning and critical thinking abilities to achieve superior performance on downstream tasks, especially those involving complex problem-solving. Our latest release, QwQ-32B, is a mid-sized model that competes effectively with top-tier reasoning models like DeepSeek-R1 and o1-mini, delivering robust and competitive results.

Qwen2.5-VL

In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL. Key Enhancements: Powerful Document Parsing Capabilities: Upgrade text recognition to omnidocument parsing, excelling in processing multi-scene, multilingual, and various built-in (handwriting, tables, charts, chemical formulas, and music sheets) documents.

vLLM V1

We are thrilled to announce the alpha release of vLLM V1, a major upgrade to vLLM’s core architecture. Based on lessons we learned over the past 1.5 years of vLLM development, we revisited key design decisions, consolidated various features, and simplified the codebase to enhance flexibility and scalability. V1 already achieves state-of-the-art performance and is set to gain even more optimizations.

DeepSeek-R1

We introduce DeepSeek’s 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 step, demonstrated remarkable performance on reasoning. DeepSeek-R1 incorporates cold-start data before RL, and achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.

DeepSeek-V3

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance.

SGLang v0.4

We’re excited to announce the release of SGLang v0.4, featuring significant performance improvements and new features: Zero-overhead batch scheduler: 1.1x increase in throughput. Cache-aware load balancer: up to 1.9x increase in throughput with 3.8x higher cache hit rate. Data parallelism attention for DeepSeek models: up to 1.9x decoding throughput improvement. Fast structured outputs with xgrammar: up to 10x faster.