---
title: PhyEduVideo
description: "WACV 2026 physics-education T2V: 60 concepts, 205 teaching-point prompts. WorldFoundry imports judge files and checks coverage — it does not run InternVL."
---

PhyEduVideo (IIIT Hyderabad, Adobe, IISER Thiruvananthapuram; WACV 2026) asks whether a T2V model can **illustrate a teaching point**, not whether it obeys a law taxonomy. The bundled `Prompts/Prompts.json` has **60 concepts** in **6 categories** (mechanics, oscillations and waves, fluids, thermodynamics, electromagnetism, optics), split into **205** visually descriptive teaching-point prompts.

That is **education**, not [PhyGenBench](/docs/evaluation/benchmark-hub/phygenbench) (27-law commonsense generation), not [PhyGround](/docs/evaluation/benchmark-hub/phyground) (13-law criteria on TI2V), and not [PhyFPS-Bench-Gen](/docs/evaluation/benchmark-hub/phyfps-bench-gen) (frame-rate audit).

Paper: [PhyEduVideo](https://arxiv.org/abs/2601.00943). Project: [meghamariamkm.github.io/phyeduvideo26](https://meghamariamkm.github.io/phyeduvideo26/). Code: [meghamariamkm/PhyEduVideo](https://github.com/meghamariamkm/PhyEduVideo).

WorldFoundry **imports** caller-supplied result files (JSON / JSONL / CSV), checks prompt/video coverage against the bundled manifests, and writes a scorecard. The InternVL / CLIP / VQA judge stack is **not** run in tree.

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

## How to run

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

`--run-official` on the dedicated runner is the same import path for WorldFoundry-generated artifacts. Outputs include `scorecard.json` (primary `phyeduvideo_average`), `results_summary.csv`, and per-sample rows when the file exposes them.

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