# Long Story Evaluation on LongStoryEval Full (test) Source: [Long Story Evaluation on LongStoryEval Full (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:06.583Z Evaluation of model performance on the full test set of the LongStoryEval benchmark, assessing narrative quality across dimensions like Plot, Character, Writing, Theme, Emotion, Enjoyment, and Overall coherence. 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 Full (test) | | Metric | Plot Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 Score](): Higher is better; unit: SCALAR. - [Character Score](): Higher is better; unit: SCALAR. - [Writing Score](): Higher is better; unit: SCALAR. - [Word Choice Score](): Higher is better; unit: SCALAR. - [Theme Score](): Higher is better; unit: SCALAR. - [Emotion Score](): Higher is better; unit: SCALAR. - [Enjoyment Score](): Higher is better; unit: SCALAR. - [Expectation Score](): Higher is better; unit: SCALAR. - [Overall Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Plot Score | Result date | Report paper | | --- | --- | --- | --- | | NovelCritique-8B | 27.1 | Not recorded | 6940e7d1456146936284fb2a | | Llama 3.1-70B | 19.6 | Not recorded | 6940e7d1456146936284fb2a | | DeepSeek-v2.5 | 17.2 | Not recorded | 6940e7d1456146936284fb2a | | Llama 3.1-8B | 15.5 | Not recorded | 6940e7d1456146936284fb2a | | GPT-4o | 15.3 | Not recorded | 6940e7d1456146936284fb2a | | GPT-4o | 14.3 | Not recorded | 6940e7d1456146936284fb2a | | GPT-4o-mini | 14.2 | Not recorded | 6940e7d1456146936284fb2a | | DeepSeek-v2.5 | 13.4 | Not recorded | 6940e7d1456146936284fb2a | | Llama 3.1-70B | 11.2 | Not recorded | 6940e7d1456146936284fb2a | | Llama 3.1-8B | 10.4 | Not recorded | 6940e7d1456146936284fb2a | | Mixtral 8x7B | 9.5 | Not recorded | 6940e7d1456146936284fb2a | | Llama 3.1-70B | 9.3 | Not recorded | 6940e7d1456146936284fb2a | | DeepSeek-v2.5 | 8.9 | Not recorded | 6940e7d1456146936284fb2a | | GPT-4o-mini | 8.7 | Not recorded | 6940e7d1456146936284fb2a | | GPT-4o | 8 | Not recorded | 6940e7d1456146936284fb2a | | GPT-4o-mini | 7.9 | Not recorded | 6940e7d1456146936284fb2a | | Mixtral 8x7B | 7.8 | Not recorded | 6940e7d1456146936284fb2a | | Llama 3.1-8B | 7 | Not recorded | 6940e7d1456146936284fb2a | | Mixtral 8x7B | 4.2 | Not recorded | 6940e7d1456146936284fb2a | ### NovelCritique-8B Plot Score: 27.1. Result ID: 6996c0d45698665ec40bffd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Summary-Based"}. This record does not assert independent reproduction. ### Llama 3.1-70B Plot Score: 19.6. Result ID: 6996c0d45698665ec40bffc3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Aggregation-Based"}. This record does not assert independent reproduction. ### DeepSeek-v2.5 Plot Score: 17.2. Result ID: 6996c0d45698665ec40bffc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Aggregation-Based"}. This record does not assert independent reproduction. ### Llama 3.1-8B Plot Score: 15.5. Result ID: 6996c0d45698665ec40bffc4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Aggregation-Based"}. This record does not assert independent reproduction. ### GPT-4o Plot Score: 15.3. Result ID: 6996c0d45698665ec40bffcc. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Summary-Based"}. This record does not assert independent reproduction. ### GPT-4o Plot Score: 14.3. Result ID: 6996c0d45698665ec40bffc0. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Aggregation-Based"}. This record does not assert independent reproduction. ### GPT-4o-mini Plot Score: 14.2. Result ID: 6996c0d45698665ec40bffc2. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Aggregation-Based"}. This record does not assert independent reproduction. ### DeepSeek-v2.5 Plot Score: 13.4. Result ID: 6996c0d45698665ec40bffcd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Summary-Based"}. This record does not assert independent reproduction. ### Llama 3.1-70B Plot Score: 11.2. Result ID: 6996c0d45698665ec40bffcf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Summary-Based"}. This record does not assert independent reproduction. ### Llama 3.1-8B Plot Score: 10.4. Result ID: 6996c0d45698665ec40bffd0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Summary-Based"}. This record does not assert independent reproduction. ### Mixtral 8x7B Plot Score: 9.5. Result ID: 6996c0d45698665ec40bffc5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Aggregation-Based"}. This record does not assert independent reproduction. ### Llama 3.1-70B Plot Score: 9.3. Result ID: 6996c0d45698665ec40bffc9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Incremental-Updated"}. This record does not assert independent reproduction. ### DeepSeek-v2.5 Plot Score: 8.9. Result ID: 6996c0d45698665ec40bffc7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Incremental-Updated"}. This record does not assert independent reproduction. ### GPT-4o-mini Plot Score: 8.7. Result ID: 6996c0d45698665ec40bffce. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Summary-Based"}. This record does not assert independent reproduction. ### GPT-4o Plot Score: 8. Result ID: 6996c0d45698665ec40bffc6. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Incremental-Updated"}. This record does not assert independent reproduction. ### GPT-4o-mini Plot Score: 7.9. Result ID: 6996c0d45698665ec40bffc8. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Strategy":"Incremental-Updated"}. This record does not assert independent reproduction. ### Mixtral 8x7B Plot Score: 7.8. Result ID: 6996c0d45698665ec40bffd1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Summary-Based"}. This record does not assert independent reproduction. ### Llama 3.1-8B Plot Score: 7. Result ID: 6996c0d45698665ec40bffca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Incremental-Updated"}. This record does not assert independent reproduction. ### Mixtral 8x7B Plot Score: 4.2. Result ID: 6996c0d45698665ec40bffcb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Strategy":"Incremental-Updated"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.