AppWorld-UL (Function Calling) - Compositional Tasks: leaderboard

Metric: Interactive task goal completion (%; share of 210 tasks combining two or three interaction types whose AppWorld unit tests all pass, including a test that the agent asked the simulated user for every piece of hidden information it needed; function-calling agent over the AppWorld app APIs; GPT-5.5 user simulator answering from a fixed knowledge set). Source: arxiv.org. Saturation forecast: Around 2030. 5 models tracked.

Top models

#ModelScore
1Claude Opus 4.720.9
2DeepSeek V4 Pro18.6
3Kimi K2.617.1
4Qwen 3.7 Max17.1
5GPT-5.5 (Medium)17.1

Interactive version: theaggregate.ai/benchmark?slug=appworld-ul-function-calling-compositional-tasks · How It Works · Data refreshed daily, snapshot 2026-09-29.