# Agentic Presentation Generation on 48 Business Briefs 1.0 (test)

Source: [Agentic Presentation Generation on 48 Business Briefs 1.0 (test)](<https://www.sota2.com/research/sota/agentic-presentation-generation-on-48-business-briefs-1-0-test>)

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

Data updated: 2026-03-18T09:26:56.738Z

Evaluation of Agentic Presentation Generation performance on the test split of the 48 Business Briefs 1.0 dataset, measured using metrics like Overall quality, Completion rate, Average turns used, Average slides created, and Average time per brief.

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 | Agentic Presentation Generation |
| Dataset (including any stated split) | 48 Business Briefs 1.0 (test) |
| Metric | Overall Quality |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Overall Quality](<https://www.sota2.com/research/sota/agentic-presentation-generation-on-48-business-briefs-1-0-test.md?metric=Overall%20Quality>): Higher is better; unit: SCALAR.

- [Completion Rate](<https://www.sota2.com/research/sota/agentic-presentation-generation-on-48-business-briefs-1-0-test.md?metric=Completion%20Rate>): Higher is better; unit: PERCENT.

- [Avg Turns Used](<https://www.sota2.com/research/sota/agentic-presentation-generation-on-48-business-briefs-1-0-test.md?metric=Avg%20Turns%20Used>): Lower is better; unit: SCALAR.

- [Avg Slides Created](<https://www.sota2.com/research/sota/agentic-presentation-generation-on-48-business-briefs-1-0-test.md?metric=Avg%20Slides%20Created>): Higher is better; unit: SCALAR.

- [Avg Time per Brief (s)](<https://www.sota2.com/research/sota/agentic-presentation-generation-on-48-business-briefs-1-0-test.md?metric=Avg%20Time%20per%20Brief%20(s)>): Lower is better; unit: TIME.

## Recorded results

| Method | Overall Quality | Result date | Report paper |
| --- | --- | --- | --- |
| Claude Opus 4.6 | 0.794 | Not recorded | 69ba31b40636e5bf4afc0a75 |
| Llama 4 Scout | 0.779 | Not recorded | 69ba31b40636e5bf4afc0a75 |
| Claude Sonnet 4.6 | 0.775 | Not recorded | 69ba31b40636e5bf4afc0a75 |
| SlideRL | 0.724 | Not recorded | 69ba31b40636e5bf4afc0a75 |
| Base Qwen | 0.544 | Not recorded | 69ba31b40636e5bf4afc0a75 |
| GPT OSS 120B | 0.249 | Not recorded | 69ba31b40636e5bf4afc0a75 |

### Claude Opus 4.6

Overall Quality: 0.794. Result ID: 69ba6fdf47f34ce924a4afcf.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b40636e5bf4afc0a75.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Llama 4 Scout

Overall Quality: 0.779. Result ID: 69ba6fdf47f34ce924a4afd1.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b40636e5bf4afc0a75.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Claude Sonnet 4.6

Overall Quality: 0.775. Result ID: 69ba6fdf47f34ce924a4afd0.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b40636e5bf4afc0a75.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SlideRL

Overall Quality: 0.724. Result ID: 69ba6fdf47f34ce924a4afcd.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b40636e5bf4afc0a75.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31b40636e5bf4afc0a75.md>)

Recorded evaluation configuration: {"Backbone":"Qwen 7B","Fine-tuned":"true","Training method":"GRPO"}. This record does not assert independent reproduction.

### Base Qwen

Overall Quality: 0.544. Result ID: 69ba6fdf47f34ce924a4afce.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b40636e5bf4afc0a75.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b71e209131cea6981e.md>)

Recorded evaluation configuration: {"Backbone":"Qwen 7B"}. This record does not assert independent reproduction.

### GPT OSS 120B

Overall Quality: 0.249. Result ID: 69ba6fdf47f34ce924a4afd2.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31b40636e5bf4afc0a75.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a0c.md>)

Recorded evaluation configuration: {"Parameters":"120B"}. This record does not assert independent reproduction.

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