# Storytelling Image Generation on GPT-image quality: medium 1.0 Source: [Storytelling Image Generation on GPT-image quality: medium 1.0]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:05:12.503Z Evaluation of models generating stories or story-related images using the GPT-image quality: medium 1.0 dataset, assessed on success rate, word count, visual clues, diversity, semantic score, and human preference. 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 | Storytelling Image Generation | | Dataset (including any stated split) | GPT-image quality: medium 1.0 | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Success Rate](): Higher is better; unit: PERCENT. - [Word Count](): Higher is better; unit: SCALAR. - [Visual Clue Count](): Higher is better; unit: SCALAR. - [Diversity](): Higher is better; unit: SCALAR. - [Semantic Score](): Higher is better; unit: SCALAR. - [Human Preference Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | Mini-Storyteller-LLaMA-3.2-1B-SFT | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Llama-3.2-3B-Instruct | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-LLaMA-3.2-3B-SFT | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-LLaMA-3.2-3B-DPO | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Llama-3.1-8B-Instruct | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-LLaMA-3.1-8B-SFT | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-LLaMA-3.1-8B-DPO | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-LLaMA-3.1-8B-DPO-Mix | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Qwen2.5-1.5B-Instruct | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-Qwen2.5-1.5B-SFT | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-Qwen2.5-1.5B-DPO | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Qwen2.5-7B-Instruct | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-Qwen2.5-7B-SFT | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-Qwen2.5-7B-DPO | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-Qwen2.5-7B-DPO-Mix | 1 | Not recorded | 6937ad546cfd488761a4ec3c | | Llama-3.2-1B-Instruct | 0.967 | Not recorded | 6937ad546cfd488761a4ec3c | | Mini-Storyteller-LLaMA-3.2-1B-DPO | 0.967 | Not recorded | 6937ad546cfd488761a4ec3c | ### Mini-Storyteller-LLaMA-3.2-1B-SFT Success Rate: 1. Result ID: 699878e55698665ec4d983a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Llama-3.2","Size":"1B","Training Strategy":"SFT","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Llama-3.2-3B-Instruct Success Rate: 1. Result ID: 699878e55698665ec4d983aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base LLM":"Llama-3.2","Size":"3B","Training Strategy":"Instruct","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-LLaMA-3.2-3B-SFT Success Rate: 1. Result ID: 699878e55698665ec4d983ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Llama-3.2","Size":"3B","Training Strategy":"SFT","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-LLaMA-3.2-3B-DPO Success Rate: 1. Result ID: 699878e55698665ec4d983ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Llama-3.2","Size":"3B","Training Strategy":"DPO","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Llama-3.1-8B-Instruct Success Rate: 1. Result ID: 699878e55698665ec4d983ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base LLM":"Llama-3.1","Size":"8B","Training Strategy":"Instruct","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-LLaMA-3.1-8B-SFT Success Rate: 1. Result ID: 699878e55698665ec4d983ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Llama-3.1","Size":"8B","Training Strategy":"SFT","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-LLaMA-3.1-8B-DPO Success Rate: 1. Result ID: 699878e55698665ec4d983af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Llama-3.1","Size":"8B","Training Strategy":"DPO","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-LLaMA-3.1-8B-DPO-Mix Success Rate: 1. Result ID: 699878e55698665ec4d983b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Llama-3.1","Size":"8B","Training Strategy":"DPO-Mix","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Qwen2.5-1.5B-Instruct Success Rate: 1. Result ID: 699878e55698665ec4d983b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen2.5","Size":"1.5B","Training Strategy":"Instruct","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-Qwen2.5-1.5B-SFT Success Rate: 1. Result ID: 699878e55698665ec4d983b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen2.5","Size":"1.5B","Training Strategy":"SFT","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-Qwen2.5-1.5B-DPO Success Rate: 1. Result ID: 699878e55698665ec4d983b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen2.5","Size":"1.5B","Training Strategy":"DPO","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Success Rate: 1. Result ID: 699878e55698665ec4d983b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen2.5","Size":"7B","Training Strategy":"Instruct","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-Qwen2.5-7B-SFT Success Rate: 1. Result ID: 699878e55698665ec4d983b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen2.5","Size":"7B","Training Strategy":"SFT","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-Qwen2.5-7B-DPO Success Rate: 1. Result ID: 699878e55698665ec4d983b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen2.5","Size":"7B","Training Strategy":"DPO","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-Qwen2.5-7B-DPO-Mix Success Rate: 1. Result ID: 699878e55698665ec4d983b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Qwen2.5","Size":"7B","Training Strategy":"DPO-Mix","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Llama-3.2-1B-Instruct Success Rate: 0.967. Result ID: 699878e55698665ec4d983a7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base LLM":"Llama-3.2","Size":"1B","Training Strategy":"Instruct","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. ### Mini-Storyteller-LLaMA-3.2-1B-DPO Success Rate: 0.967. Result ID: 699878e55698665ec4d983a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base LLM":"Llama-3.2","Size":"1B","Training Strategy":"DPO","Painter Model":"GPT-image-1 (medium)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.