# Long Story Evaluation on LongStoryEval 128K token context

Source: [Long Story Evaluation on LongStoryEval 128K token context](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context>)

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

Data updated: 2026-02-26T05:58:06.409Z

Evaluation of model performance on the LongStoryEval dataset, specifically assessing narrative quality metrics across a 128K token context length.

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 | Long Story Evaluation |
| Dataset (including any stated split) | LongStoryEval 128K token context |
| Metric | Plot Quality |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Plot Quality](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Plot%20Quality>): Higher is better; unit: SCALAR.

- [Coherence](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Coherence>): Higher is better; unit: SCALAR.

- [Writing Quality](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Writing%20Quality>): Higher is better; unit: SCALAR.

- [Word Choice](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Word%20Choice>): Higher is better; unit: SCALAR.

- [Theme Relevance](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Theme%20Relevance>): Higher is better; unit: SCALAR.

- [Emotional Resonance](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Emotional%20Resonance>): Higher is better; unit: SCALAR.

- [Engagement](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Engagement>): Higher is better; unit: SCALAR.

- [Exposition Quality](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Exposition%20Quality>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/long-story-evaluation-on-longstoryeval-128k-token-context.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Plot Quality | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-v2.5 | 4.4 | Not recorded | 6940e7d1456146936284fb2a |
| GPT-4o | 3.3 | Not recorded | 6940e7d1456146936284fb2a |

### DeepSeek-v2.5

Plot Quality: 4.4. Result ID: 6996c0d45698665ec40bffbf.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7d1456146936284fb2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73b81e209131cea5e189.md>)

Recorded evaluation configuration: {"Evaluation Strategy":"One-Pass"}. This record does not assert independent reproduction.

### GPT-4o

Plot Quality: 3.3. Result ID: 6996c0d45698665ec40bffbe.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7d1456146936284fb2a.md>)

Recorded evaluation configuration: {"Evaluation Strategy":"One-Pass"}. This record does not assert independent reproduction.

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