AsyncPlan Robo Challenge (Planner): leaderboard

Metric: Plan accuracy (%; share of the 140 Robo Challenge kitchen tasks (seven splits of 20 built on Robotouille, with object states, resources, stations and multiple agents) whose plan is valid and reaches the optimal makespan; the LLM writes the schedule directly (Planner); zero-shot, temperature 0). Source: arxiv.org. Saturation forecast: Around 2032. 4 models tracked.

Top models

#ModelScore
1Qwen 3.6 35B A3B59.3
2GPT-5 Mini46.4
3Gemini 3 Flash40.7
4DeepSeek V4 Flash12.9

Interactive version: theaggregate.ai/benchmark?slug=asyncplan-robo-challenge-planner · How It Works · Data refreshed daily, snapshot 2026-09-26.