Storytelling Image Generation on CogBench ISA (test)
459.27Story Length (Words)StorytellingPainter
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| StorytellingPainterMode=CoR-Guided, Storyteller=Llama-3.2-1B-Instruct, Painter=DALL-E 32025.12 | 459.27 | 90 | 7.33 | 0.432 | 28.1 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Llama-3.2-1B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 459.27 | 96.7 | 7.17 | 0.432 | 36.5 | 38.6 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Qwen2.5-1.5B-Instruct, Painter=DALL-E 32025.12 | 443.2 | 93.3 | 8.04 | 0.407 | 29.1 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Qwen2.5-1.5B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 443.2 | 100 | 8.13 | 0.407 | 31.1 | 29.9 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Qwen2.5-1.5B-Instruct, Painter=GPT-image-1, Quality setting=auto2025.12 | 443.2 | 100 | 7.3 | 0.407 | 32.8 | 34.7 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Llama-3.2-3B-Instruct, Painter=DALL-E 32025.12 | 389.77 | 100 | 7.4 | 0.35 | 31.5 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Llama-3.2-3B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 389.77 | 100 | 7.8 | 0.35 | 36.3 | 35.6 | |
| StorytellingPainterMode=Naive, Storyteller=Llama-3.2-1B-Instruct, Painter=DALL-E 32025.12 | 384.33 | 100 | 7 | 0.382 | 17.2 | — | |
| StorytellingPainterMode=Naive, Storyteller=Llama-3.2-1B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 384.33 | 100 | 6.1 | 0.382 | 18.1 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Llama-3.1-8B-Instruct, Painter=DALL-E 32025.12 | 359.27 | 100 | 7.37 | 0.374 | 25.2 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Llama-3.1-8B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 359.27 | 100 | 7.53 | 0.374 | 34.2 | 32.1 | |
| StorytellingPainterMode=Naive, Storyteller=Llama-3.1-8B-Instruct, Painter=DALL-E 32025.12 | 351.77 | 100 | 6.7 | 0.337 | 13.1 | — | |
| StorytellingPainterMode=Naive, Storyteller=Llama-3.1-8B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 351.77 | 96.7 | 6.38 | 0.337 | 13 | — | |
| StorytellingPainterMode=Naive, Storyteller=Llama-3.2-3B-Instruct, Painter=DALL-E 32025.12 | 339.87 | 100 | 6.2 | 0.25 | 11.8 | — | |
| StorytellingPainterMode=Naive, Storyteller=Llama-3.2-3B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 339.87 | 100 | 6.5 | 0.25 | 10 | — | |
| StorytellingPainterMode=Naive, Storyteller=Qwen2.5-1.5B-Instruct, Painter=DALL-E 32025.12 | 311.33 | 96.7 | 7.31 | 0.365 | 16.3 | — | |
| StorytellingPainterMode=Naive, Storyteller=Qwen2.5-1.5B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 311.33 | 100 | 6.9 | 0.365 | 17.3 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=GPT-4o-mini, Painter=DALL-E 32025.12 | 183.13 | 100 | 8.83 | 0.367 | 56.8 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=GPT-4o-mini, Painter=GPT-image-1, Quality setting=medium2025.12 | 183.13 | 100 | 8.37 | 0.367 | 56.7 | 52.4 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=GPT-4o-mini, Painter=GPT-image-1, Quality setting=auto2025.12 | 183.13 | 100 | 8.93 | 0.367 | 61 | 62.9 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=GPT-4o, Painter=DALL-E 32025.12 | 179.1 | 100 | 8.17 | 0.393 | 49.3 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=GPT-4o, Painter=GPT-image-1, Quality setting=medium2025.12 | 179.1 | 100 | 9 | 0.393 | 52.4 | 57.6 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=GPT-4o, Painter=GPT-image-1, Quality setting=auto2025.12 | 179.1 | 100 | 8.53 | 0.393 | 52.1 | 57.6 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Qwen2.5-7B-Instruct, Painter=DALL-E 32025.12 | 165.83 | 100 | 7.83 | 0.381 | 34.7 | — | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Qwen2.5-7B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 165.83 | 100 | 7.87 | 0.381 | 37.2 | 37.8 | |
| StorytellingPainterMode=CoR-Guided, Storyteller=Qwen2.5-7B-Instruct, Painter=GPT-image-1, Quality setting=auto2025.12 | 165.83 | 100 | 8.07 | 0.381 | 38.9 | 44.6 | |
| StorytellingPainterMode=Naive, Storyteller=GPT-4o, Painter=DALL-E 32025.12 | 144.07 | 100 | 8.37 | 0.312 | 34.1 | — | |
| StorytellingPainterMode=Naive, Storyteller=GPT-4o, Painter=GPT-image-1, Quality setting=medium2025.12 | 144.07 | 100 | 7.1 | 0.312 | 31.5 | — | |
| CogBenchContext=ISA test set, Top-K selection=top-302025.12 | 135.93 | — | 9.13 | 0.441 | 59.2 | 71.8 | |
| CogBenchContext=ISA test set2025.12 | 119.9 | — | 8.83 | 0.425 | 57.6 | 66.7 | |
| StorytellingPainterMode=Naive, Storyteller=GPT-4o-mini, Painter=DALL-E 32025.12 | 111.37 | 100 | 8.37 | 0.262 | 39.1 | — | |
| StorytellingPainterMode=Naive, Storyteller=GPT-4o-mini, Painter=GPT-image-1, Quality setting=medium2025.12 | 111.37 | 100 | 8.53 | 0.262 | 40.7 | — | |
| StorytellingPainterMode=Naive, Storyteller=Qwen2.5-7B-Instruct, Painter=DALL-E 32025.12 | 92.5 | 100 | 7.53 | 0.272 | 26.6 | — | |
| StorytellingPainterMode=Naive, Storyteller=Qwen2.5-7B-Instruct, Painter=GPT-image-1, Quality setting=medium2025.12 | 92.5 | 100 | 7.17 | 0.272 | 26.2 | — |