# Interactive Document Generation on ViviBench Human Evaluation (9 topics)

Source: [Interactive Document Generation on ViviBench Human Evaluation (9 topics)](<https://www.sota2.com/research/sota/interactive-document-generation-on-vivibench-human-evaluation-9-topics>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-31T10:41:10.581Z

Human evaluation of models performing Interactive Document Generation using the ViviBench dataset, focusing on Content Richness and Interaction Design.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Interactive Document Generation |
| Dataset (including any stated split) | ViviBench Human Evaluation (9 topics) |
| Metric | Content Richness (CR) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Content Richness (CR)](<https://www.sota2.com/research/sota/interactive-document-generation-on-vivibench-human-evaluation-9-topics.md?metric=Content%20Richness%20(CR)>): Higher is better; unit: SCALAR.

- [Interaction Design (ID)](<https://www.sota2.com/research/sota/interactive-document-generation-on-vivibench-human-evaluation-9-topics.md?metric=Interaction%20Design%20(ID)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Content Richness (CR) | Result date | Report paper |
| --- | --- | --- | --- |
| ViviDoc | 4.43 | Not recorded | 69cb55390636e5bf4afca0d3 |
| AutoGen | 2.79 | Not recorded | 69cb55390636e5bf4afca0d3 |
| MetaGPT | 2.51 | Not recorded | 69cb55390636e5bf4afca0d3 |
| CAMEL | 1.6 | Not recorded | 69cb55390636e5bf4afca0d3 |

### ViviDoc

Content Richness (CR): 4.43. Result ID: 69cba3f647f34ce924b49e56.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55390636e5bf4afca0d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb55390636e5bf4afca0d3.md>)

Recorded evaluation configuration: {"Backbone":"Gemini 3 Flash"}. This record does not assert independent reproduction.

### AutoGen

Content Richness (CR): 2.79. Result ID: 69cba3f647f34ce924b49e53.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55390636e5bf4afca0d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70cd1e209131cea4d3e0.md>)

Recorded evaluation configuration: {"Backbone":"Gemini 3 Flash"}. This record does not assert independent reproduction.

### MetaGPT

Content Richness (CR): 2.51. Result ID: 69cba3f647f34ce924b49e54.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55390636e5bf4afca0d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea68673.md>)

Recorded evaluation configuration: {"Backbone":"Gemini 3 Flash"}. This record does not assert independent reproduction.

### CAMEL

Content Richness (CR): 1.6. Result ID: 69cba3f647f34ce924b49e55.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55390636e5bf4afca0d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1bf.md>)

Recorded evaluation configuration: {"Backbone":"Gemini 3 Flash"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.