# Text-to-Stage on PDNC 2 (val)

Source: [Text-to-Stage on PDNC 2 (val)](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val>)

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

Data updated: 2026-03-19T10:03:41.208Z

Evaluation of Text-to-Stage generation performance on the validation split of the PDNC 2 dataset, measuring specific aspects like quote attribution, alias resolution, and scene transitions.

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 | Text-to-Stage |
| Dataset (including any stated split) | PDNC 2 (val) |
| Metric | Quote Attribution |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Quote Attribution](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val.md?metric=Quote%20Attribution>): Higher is better; unit: PERCENT.

- [Alias Resolution](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val.md?metric=Alias%20Resolution>): Higher is better; unit: PERCENT.

- [Stage Position Accuracy](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val.md?metric=Stage%20Position%20Accuracy>): Higher is better; unit: PERCENT.

- [Character Position Accuracy](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val.md?metric=Character%20Position%20Accuracy>): Higher is better; unit: PERCENT.

- [Movement Coherence](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val.md?metric=Movement%20Coherence>): Higher is better; unit: PERCENT.

- [Scene Transition Accuracy](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val.md?metric=Scene%20Transition%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/text-to-stage-on-pdnc-2-val.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Quote Attribution | Result date | Report paper |
| --- | --- | --- | --- |
| Claude Sonnet 3.5 | 96 | Not recorded | 69bb83070636e5bf4afc19fc |
| Claude Sonnet 4 | 96 | Not recorded | 69bb83070636e5bf4afc19fc |
| Llama-4-Maverick | 96 | Not recorded | 69bb83070636e5bf4afc19fc |
| GPT-4o | 95 | Not recorded | 69bb83070636e5bf4afc19fc |
| GPT-4.1 | 94 | Not recorded | 69bb83070636e5bf4afc19fc |
| Claude Sonnet 3.7 | 94 | Not recorded | 69bb83070636e5bf4afc19fc |
| Gemini-2.0-flash | 93 | Not recorded | 69bb83070636e5bf4afc19fc |
| Spatializer-SFT | 92.8 | Not recorded | 69bb83070636e5bf4afc19fc |
| Llama-3.3-70B-it | 92.5 | Not recorded | 69bb83070636e5bf4afc19fc |
| Llama-4-Scout | 92 | Not recorded | 69bb83070636e5bf4afc19fc |
| Spatializer-GRPO | 91.8 | Not recorded | 69bb83070636e5bf4afc19fc |
| Gemma-3-27b-it | 89.1 | Not recorded | 69bb83070636e5bf4afc19fc |
| Llama-3.3-8B-it | 86.8 | Not recorded | 69bb83070636e5bf4afc19fc |
| Qwen3-8b | 83.8 | Not recorded | 69bb83070636e5bf4afc19fc |
| Llama-3.1-8B-it | 27 | Not recorded | 69bb83070636e5bf4afc19fc |

### Claude Sonnet 3.5

Quote Attribution: 96. Result ID: 69bbc9f347f34ce924a6420e.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary models"}. This record does not assert independent reproduction.

### Claude Sonnet 4

Quote Attribution: 96. Result ID: 69bbc9f347f34ce924a64211.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary models"}. This record does not assert independent reproduction.

### Llama-4-Maverick

Quote Attribution: 96. Result ID: 69bbc9f347f34ce924a64216.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Open-source models"}. This record does not assert independent reproduction.

### GPT-4o

Quote Attribution: 95. Result ID: 69bbc9f347f34ce924a64210.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary models"}. This record does not assert independent reproduction.

### GPT-4.1

Quote Attribution: 94. Result ID: 69bbc9f347f34ce924a6420f.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary models"}. This record does not assert independent reproduction.

### Claude Sonnet 3.7

Quote Attribution: 94. Result ID: 69bbc9f347f34ce924a64213.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary models"}. This record does not assert independent reproduction.

### Gemini-2.0-flash

Quote Attribution: 93. Result ID: 69bbc9f347f34ce924a64212.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Proprietary models"}. This record does not assert independent reproduction.

### Spatializer-SFT

Quote Attribution: 92.8. Result ID: 69bbc9f347f34ce924a6421b.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Our models"}. This record does not assert independent reproduction.

### Llama-3.3-70B-it

Quote Attribution: 92.5. Result ID: 69bbc9f347f34ce924a64215.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Open-source models"}. This record does not assert independent reproduction.

### Llama-4-Scout

Quote Attribution: 92. Result ID: 69bbc9f347f34ce924a64214.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Open-source models"}. This record does not assert independent reproduction.

### Spatializer-GRPO

Quote Attribution: 91.8. Result ID: 69bbc9f347f34ce924a6421c.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Our models"}. This record does not assert independent reproduction.

### Gemma-3-27b-it

Quote Attribution: 89.1. Result ID: 69bbc9f347f34ce924a64218.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Open-source models"}. This record does not assert independent reproduction.

### Llama-3.3-8B-it

Quote Attribution: 86.8. Result ID: 69bbc9f347f34ce924a64217.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

Recorded evaluation configuration: {"Model Category":"Open-source models"}. This record does not assert independent reproduction.

### Qwen3-8b

Quote Attribution: 83.8. Result ID: 69bbc9f347f34ce924a64219.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Category":"Open-source models"}. This record does not assert independent reproduction.

### Llama-3.1-8B-it

Quote Attribution: 27. Result ID: 69bbc9f347f34ce924a6421a.

[Reporting paper](<https://www.sota2.com/research/paper/69bb83070636e5bf4afc19fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Model Category":"Open-source models"}. This record does not assert independent reproduction.

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