---
title: VBench++
description: "VBench extensions: I2V, long-video, trustworthiness. WorldFoundry vendors the runtime; it does not invent a board. Distinct from VBench and VBench-2.0."
---

VBench++ (S-Lab, NTU and Shanghai AI Laboratory) extends [VBench](/docs/evaluation/benchmark-hub/vbench) with three tracks. It is **not** [VBench-2.0](/docs/evaluation/benchmark-hub/vbench-2.0). Same upstream repo: [Vchitect/VBench](https://github.com/Vchitect/VBench) (Apache-2.0).

- **Image-to-video** — I2V subject / background consistency and camera motion on the official crop-ready image suite.
- **Long-video** — temporal-window scoring; the catalog-bounded command uses `temporal_flickering` / `long_custom_input`.
- **Trustworthiness** — fairness, bias, safety probes (some need extra face / attribute models).

`--variant` selects `i2v`, `long`, or `trustworthiness`. Per-variant averages plus `vbench_plus_plus_average` (WorldFoundry mean over available dims).

Paper: [VBench++](https://arxiv.org/abs/2411.13503). Project: [vchitect.github.io/VBench-project](https://vchitect.github.io/VBench-project/).

WorldFoundry **vendors the VBench++ runtime**. A bounded long-video component is verified; the complete suite is not.

<BenchmarkPageSections id="vbench-plus-plus" locale="en" />

## How to run

```bash
${WORLDFOUNDRY_UNIFIED_PYTHON} \
  worldfoundry/evaluation/tasks/execution/runners/vbench_plus_plus/run_vbench_plus_plus_official_runner.py \
  --benchmark-id vbench-plus-plus \
  --variant long \
  --videos-path "${WORLDFOUNDRY_GENERATED_ARTIFACT_DIR}" \
  --dimension temporal_flickering \
  --mode long_custom_input \
  --python "${WORLDFOUNDRY_UNIFIED_PYTHON}" \
  --output-dir tmp/vbench-plus-plus/long \
  --json
```

I2V uses official image-suite naming. Optional checkout override: `WORLDFOUNDRY_VBENCH_PLUS_PLUS_ROOT`. Shared stack: `vbench_perception_metric_stack`. Prompt / image suites live in the public VBench repo.

In-tree pointers: `worldfoundry/data/benchmarks/tasks/external/vbench-plus-plus.yaml`, `worldfoundry/evaluation/tasks/execution/runners/vbench_plus_plus/runtime`.

Outputs include `scorecard.json` (primary `vbench_plus_plus_average`) and `dimension_scores.json`.

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