🟣New: Qwen3-Coder by @Alibaba_Qwen - 480B params (35B active) - Native 256K context length, extrapolates to 1M - Outperforms Kimi, o3, DeepSeek, and more on SWE-Bench Verified (69.6%) 👀 Now live, starting at $1/M tokens 👇
Play with it here:
🎁 You can also get started with the smaller Qwen3 for free:
📊 SWE-Bench Verified results (500 turns) - Claude Sonnet-4: 70.4% - **Qwen3-Coder: 69.6%** - OpenAI o3: 69.1% - Kimi-K2: 65.4% - GPT-4.1: 54.6% - DeepSeek-V3: 38.8% Qwen3-Coder leads all open models, rivaling Claude and outperforming OpenAI o3
51,02K