# Story Generation on HANNA 1.0 (test) Source: [Story Generation on HANNA 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-17T07:09:55.513Z Evaluation of story generation models on the test split of the HANNA 1.0 dataset, assessed using human evaluation metrics covering narrative quality aspects like Relevance, Coherence, Empathy, Surprise, Engagement, and Complexity. 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 | Story Generation | | Dataset (including any stated split) | HANNA 1.0 (test) | | Metric | Overall Score | | 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 - [Overall Score](): Higher is better; unit: SCALAR. - [Relevance Score](): Higher is better; unit: SCALAR. - [Coherence Score](): Higher is better; unit: SCALAR. - [Empathy Score](): Higher is better; unit: SCALAR. - [Surprise Score](): Higher is better; unit: SCALAR. - [Engagement Score](): Higher is better; unit: SCALAR. - [Complexity Score](): Higher is better; unit: SCALAR. - [Standard Deviation](): Lower is better; unit: SCALAR. ## Recorded results | Method | Overall Score | Result date | Report paper | | --- | --- | --- | --- | | EvolvR GRPO | 3.59 | Not recorded | 68fa7a871e209131cea83b76 | | Qwen2.5-7B-Instruct + Point-RM GRPO | 3.542 | Not recorded | 68fa7a871e209131cea83b76 | | Qwen2.5-7B-Instruct | 3.465 | Not recorded | 68fa7a871e209131cea83b76 | | Qwen2.5-7B-Instruct + SFT | 3.169 | Not recorded | 68fa7a871e209131cea83b76 | ### EvolvR GRPO Overall Score: 3.59. Result ID: 69b8fd2c47f34ce924a0f55e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Training Method":"EvolvR GRPO","Evaluation Protocol":"Human Evaluation"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct + Point-RM GRPO Overall Score: 3.542. Result ID: 69b8fd2c47f34ce924a0f55d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Training Method":"Point-RM GRPO","Evaluation Protocol":"Human Evaluation"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Overall Score: 3.465. Result ID: 69b8fd2c47f34ce924a0f55b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Training Method":"Instruction Tuning","Evaluation Protocol":"Human Evaluation"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct + SFT Overall Score: 3.169. Result ID: 69b8fd2c47f34ce924a0f55c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Training Method":"SFT","Evaluation Protocol":"Human Evaluation"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.