# Storytelling Image Generation on CogBench ISA (test) Source: [Storytelling Image Generation on CogBench ISA (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:48.285Z Evaluation of models performing Storytelling Image Generation on the test split of the CogBench ISA dataset, measured by success rate, story length, visual clue usage, diversity, and semantic scores. 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) | CogBench ISA (test) | | Metric | Story Length (Words) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 34 of 34 | | 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 - [Story Length (Words)](): Higher is better; unit: SCALAR. - [Success Rate](): Higher is better; unit: PERCENT. - [Visual Clues Used](): Higher is better; unit: SCALAR. - [Diversity Score](): Higher is better; unit: SCALAR. - [Semantic Score](): Higher is better; unit: SCALAR. - [Human Semantic Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Story Length (Words) | Result date | Report paper | | --- | --- | --- | --- | | StorytellingPainter | 459.27 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 459.27 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 443.2 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 443.2 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 443.2 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 389.77 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 389.77 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 384.33 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 384.33 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 359.27 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 359.27 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 351.77 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 351.77 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 339.87 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 339.87 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 311.33 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 311.33 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 183.13 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 183.13 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 183.13 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 179.1 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 179.1 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 179.1 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 165.83 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 165.83 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 165.83 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 144.07 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 144.07 | Not recorded | 6937ad546cfd488761a4ec3c | | CogBench | 135.93 | Not recorded | 6937ad546cfd488761a4ec3c | | CogBench | 119.9 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 111.37 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 111.37 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 92.5 | Not recorded | 6937ad546cfd488761a4ec3c | | StorytellingPainter | 92.5 | Not recorded | 6937ad546cfd488761a4ec3c | ### StorytellingPainter Story Length (Words): 459.27. Result ID: 699878e55698665ec4d98393. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Llama-3.2-1B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 459.27. Result ID: 699878e55698665ec4d98394. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Llama-3.2-1B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 443.2. Result ID: 699878e55698665ec4d98399. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Qwen2.5-1.5B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 443.2. Result ID: 699878e55698665ec4d9839a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Qwen2.5-1.5B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 443.2. Result ID: 699878e55698665ec4d9839b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Qwen2.5-1.5B-Instruct","Painter":"GPT-image-1","Quality setting":"auto"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 389.77. Result ID: 699878e55698665ec4d98395. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Llama-3.2-3B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 389.77. Result ID: 699878e55698665ec4d98396. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Llama-3.2-3B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 384.33. Result ID: 699878e55698665ec4d98385. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Llama-3.2-1B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 384.33. Result ID: 699878e55698665ec4d98386. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Llama-3.2-1B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 359.27. Result ID: 699878e55698665ec4d98397. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Llama-3.1-8B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 359.27. Result ID: 699878e55698665ec4d98398. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Llama-3.1-8B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 351.77. Result ID: 699878e55698665ec4d98389. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Llama-3.1-8B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 351.77. Result ID: 699878e55698665ec4d9838a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Llama-3.1-8B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 339.87. Result ID: 699878e55698665ec4d98387. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Llama-3.2-3B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 339.87. Result ID: 699878e55698665ec4d98388. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Llama-3.2-3B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 311.33. Result ID: 699878e55698665ec4d9838b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Qwen2.5-1.5B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 311.33. Result ID: 699878e55698665ec4d9838c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Qwen2.5-1.5B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 183.13. Result ID: 699878e55698665ec4d983a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"GPT-4o-mini","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 183.13. Result ID: 699878e55698665ec4d983a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"GPT-4o-mini","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 183.13. Result ID: 699878e55698665ec4d983a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"GPT-4o-mini","Painter":"GPT-image-1","Quality setting":"auto"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 179.1. Result ID: 699878e55698665ec4d9839f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"GPT-4o","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 179.1. Result ID: 699878e55698665ec4d983a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"GPT-4o","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 179.1. Result ID: 699878e55698665ec4d983a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"GPT-4o","Painter":"GPT-image-1","Quality setting":"auto"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 165.83. Result ID: 699878e55698665ec4d9839c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Qwen2.5-7B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 165.83. Result ID: 699878e55698665ec4d9839d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Qwen2.5-7B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 165.83. Result ID: 699878e55698665ec4d9839e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"CoR-Guided","Storyteller":"Qwen2.5-7B-Instruct","Painter":"GPT-image-1","Quality setting":"auto"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 144.07. Result ID: 699878e55698665ec4d9838f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"GPT-4o","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 144.07. Result ID: 699878e55698665ec4d98390. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"GPT-4o","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### CogBench Story Length (Words): 135.93. Result ID: 699878e55698665ec4d983a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"ISA test set","Top-K selection":"top-30"}. This record does not assert independent reproduction. ### CogBench Story Length (Words): 119.9. Result ID: 699878e55698665ec4d983a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context":"ISA test set"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 111.37. Result ID: 699878e55698665ec4d98391. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"GPT-4o-mini","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 111.37. Result ID: 699878e55698665ec4d98392. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"GPT-4o-mini","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 92.5. Result ID: 699878e55698665ec4d9838d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Qwen2.5-7B-Instruct","Painter":"DALL-E 3"}. This record does not assert independent reproduction. ### StorytellingPainter Story Length (Words): 92.5. Result ID: 699878e55698665ec4d9838e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Naive","Storyteller":"Qwen2.5-7B-Instruct","Painter":"GPT-image-1","Quality setting":"medium"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.