🏆 CIBench Leaderboard 🏆

CIBench: Evaluating Your LLMs with a Code Interpreter Plugin

code Code description Project Page

CIBench Scores. The prefix E and O denotes the End-to-end and Oracle mode respectively. Avg is the mean of Num, Text, and Vis in two modes.

📝 Notes

Models labeled with 🌍 are API-Based models, while others are open-sourced.
Feel free to file a request to add your models on our leaderboard via open-compass.

This webpage template was recycled from here.