StepFun's new open-source model, Step 3.7 Flash, has achieved the top position on Artificial Analysis's Output Speed leaderboard, processing 409 tokens per second. The model also leads in other key metrics like end-to-end response time and intelligence versus output speed. This development highlights advancements in AI model efficiency and performance. AI
IMPACT Sets a new standard for AI model output speed, potentially influencing future model development and deployment strategies.
RANK_REASON The cluster reports on a new model release and its performance on benchmarks, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →