Exgentic

What Exgentic is

Exgentic is an open-source leaderboard and evaluation framework for comparing general-purpose AI agents. It provides a shared interface across benchmarks and domains including personal assistance, customer service, technical support, deep research, and software engineering. Listed benchmarks include τ²-bench, AppWorld, BrowseComp+, SWE-Bench, HotpotQA, GSM8K, and the Berkeley Function Calling Leaderboard. Listed agents include LiteLLM Tool Calling, SmolAgents, OpenAI MCP, Claude Code, Codex CLI, and Gemini CLI. Exgentic says it avoids prompt optimization and reports results from 100 sampled tasks per benchmark. Benchmark content and agent implementations are left unchanged, although interfaces may be adapted to a unified protocol. The repository contains the evaluation pipeline, implementations, configuration, and results for reproduction, with outcomes potentially varying by model version or nondeterministic output. Users can install a command-line tool or Python library, use OpenAI, Anthropic, or Hugging Face models, and run evaluations in Docker isolation. It is licensed under Apache License 2.0.