---
title: VideoScience-Bench
description: "UCSD Hao AI Lab science-understanding T2V bench: 1-4 rubric across five dimensions. WorldFoundry wires the VLM judge; it does not invent a board."
---

VideoScience-Bench (Hao AI Lab, UC San Diego) asks whether video generators **understand science**. Prompts describe real experiments and phenomena. A VLM judge scores five dimensions on a **1–4 rubric**; the official weighted overall normalizes to the unit interval as `videoscience_average`:

- **Prompt consistency**
- **Phenomenon congruency** — does the depicted outcome match the true science?
- **Correct dynamism**
- **Immutability** — do invariant properties stay invariant?
- **Spatio-temporal coherence**

Paper: [VideoScience-Bench](https://arxiv.org/abs/2512.02942). Space: [lmgame/videoscience-bench](https://huggingface.co/spaces/lmgame/videoscience-bench/blob/main/README.md). Code: [hao-ai-lab/VideoScience](https://github.com/hao-ai-lab/VideoScience). Catalog release status: experimental. No Hugging Face dataset is required by the contract.

WorldFoundry **normalizes official result files** and can drive judge runs over an experiments CSV when a provider / model / credential is configured. No complete credentialed upstream run is claimed.

<BenchmarkPageSections id="videoscience-bench" locale="en" />

## How to run

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

Runtime CLI takes `--experiments-csv`, `--evaluation-results-dir`, optional `--reference-videos-dir`, and judge flags (`--judge-provider`, `--judge-model`, `--judge-max-runs`, `--max-frames`, `--judge-fps`). `--ready-only` scores only complete artifacts. Default import: `WORLDFOUNDRY_VIDEOSCIENCE_BENCH_RESULTS_PATH`.

In-tree pointers: `worldfoundry/data/benchmarks/tasks/external/videoscience-bench.yaml`, `worldfoundry/evaluation/tasks/execution/runners/videoscience_bench/runtime/videoscience_bench`.

Outputs include `scorecard.json` (primary `videoscience_average`).

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