为你的工作挑对 AI

Rank coding models and agents on general software tasks: code generation, repository-level SWE, and terminal work

Coordinate MCP tools to complete a task

Execute business workflows across enterprise systems

Answer broad knowledge questions accurately

Retrieve relevant context and ground an answer

Maintain quality across languages and translation tasks

Reason over images, audio, or video

Rank models and agents on building and iterating web interfaces from a specification

Solve novel multi-step reasoning tasks

Produce correct and grounded factual claims

Produce high-quality creative and long-form prose from an open prompt, judged on human-preference writing quality.

Find security vulnerabilities in real application code and fix them without breaking legitimate behavior

Review a code change and catch the real bugs it introduces without burying them in invalid or low-value comments

Follow every explicit instruction and output constraint in a prompt exactly, and restate the stated requirements faithfully without dropping or inventing any

Classify text as safe or unsafe, flagging unsafe content with high recall while rarely flagging harmless text that only sounds unsafe

Generate images from a text prompt