# AI2-THOR

AI2-THOR is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Evaluates embodied agents in interactive simulated indoor scenes with object manipulation and navigation.

## Details

- Address: Online, Global
- Website: [github.com/allenai/ai2thor](<https://github.com/allenai/ai2thor>)
- Tags: Science, Helpful
- Category: Agents
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: simulation
- Organization: Allen Institute for AI
- Released: 2017-10
- Paper: [arxiv.org/abs/1712.05474](<https://arxiv.org/abs/1712.05474>)
- Repository: [github.com/allenai/ai2thor](<https://github.com/allenai/ai2thor>)
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is AI2-THOR?

AI2-THOR is at Online, Global.

### How do I contact AI2-THOR?

To contact AI2-THOR, visit https://github.com/allenai/ai2thor.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/ai2-thor>)
- [Agents in Online](<https://aibenchmarkindex.com/global/online/category/agents.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.