LongAct (HoloMind Agent): leaderboard
LongAct (Zhu et al., Chinese Academy of Sciences, 2026) long-horizon household benchmark: from a free-form instruction for a routine of about nine goals in a multi-room AI2-THOR house, the agent must navigate and manipulate objects (pick and place, open and close, toggle, slice) with RGB-D and segmentation observations and up to 16,000 steps. Here the listed model runs every module of the authors' HoloMind agent (DAG task planner, executor, spatial and episodic memory, critic). The score is goal completion in percent, the share of checklist objects left in the required state, on the detailed-instruction split; higher is better.
Metric: Goal completion (%; detailed-instruction split, every module of the HoloMind agent run by the listed model). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 59 | #163 |
| 2 | GPT-5 Mini | 38.4 | #349 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=longact-holomind-agent · How It Works · Data refreshed daily, snapshot 2026-11-12.