OpenAI is discontinuing its Evals service, with read-only access ending October 31st and full inaccessibility by November 30th. The Agent Builder and v1/prompts API will also be discontinued on the latter date. Users are advised to migrate their evals to Promptfoo, export results, or retrieve data via the Evals API to rebuild tests. The author introduces LLMShift, a tool designed to help users export their OpenAI Evals and run them against any LLM, including models from Anthropic. AI
IMPACT Users must migrate their LLM evaluation workflows to alternative tools like Promptfoo or LLMShift to continue testing models.
RANK_REASON The article describes a tool (LLMShift) for migrating from a discontinued service (OpenAI Evals).
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →