---
title: MolmoSpaces-Bench
description: "Ai2 MolmoBot eval ladder: 1,000-episode pick and pick-and-place. WorldFoundry imports rollouts; it does not ingest the official board."
---

MolmoSpaces-Bench is Allen Institute for AI's **simulation eval** for MolmoBot / MolmoSpaces spatial-language manipulation. The paper's training dump (**MolmoBot-Data**) is **1.7 million** expert trajectories in an ecosystem cited as **232k** environments and **48k** manipulable objects — that is **not** the bench. The bench is a **1,000-episode** ladder: Pick MSProc / Classic / photorealistic Pick / Pick Random-Cam (20 s), then Pick&Place, PnP Next-To (5 cm), PnP Color (40 s). Official tables split **pick-stage** success from **final** / oracle success. A public board lives at [molmospaces.allen.ai/leaderboard](https://molmospaces.allen.ai/leaderboard); this hub has **not** ingested its rows.

Paper: [MolmoBot](https://arxiv.org/abs/2603.16861). Project: [allenai.github.io/MolmoBot](https://allenai.github.io/MolmoBot/). Code: [allenai/MolmoBot](https://github.com/allenai/MolmoBot). WorldFoundry's contract split name is `pick_and_place`.

WorldFoundry **imports** official rollout exports. It does **not** run MolmoSpaces, generate the 1.7M set, or copy the Ai2 board into this page.

<BenchmarkPageSections id="molmospaces" locale="en" />

## How to run

```bash
worldfoundry-eval zoo benchmark-run \
  --benchmark-id molmospaces \
  --mode official-validation \
  --official-results-path <official_results.json> \
  --output-dir tmp/molmospaces/official-validation \
  --json
```

Optional `WORLDFOUNDRY_MOLMOSPACES_ROOT` points at a local runtime/repo. Default import path: `WORLDFOUNDRY_MOLMOSPACES_RESULTS_PATH`. Manifest: `worldfoundry/data/benchmarks/tasks/external/molmospaces.yaml`. Outputs: `scorecard.json` (primary `success_rate`; also `pick_success_rate`), `raw_results.jsonl`, `evaluation/summary.json`.

[← Benchmark Hub](/docs/evaluation/benchmark-hub)