AppWorld-UL (Code Agent) - Confirmation Tasks: leaderboard

Metric: Interactive task goal completion (%; share of 102 tasks whose actions need explicit user confirmation first whose AppWorld unit tests all pass, including a test that the agent asked the simulated user for every piece of hidden information it needed; ReAct code agent that writes Python against the AppWorld app APIs; GPT-5.5 user simulator answering from a fixed knowledge set). Source: arxiv.org. Saturation forecast: Around April 2027. 6 models tracked.

Top models

#ModelScore
1Qwen 3.7 Max67.7
2GLM-5.166.7
3Claude Opus 4.760.8
4GPT-5.5 (Medium)58.8
5Kimi K2.650
6DeepSeek V4 Pro48

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