ViStoryBench
Models turn stories and character references into coherent image sequences. Model judgments and image features measure prompt alignment, character consistency, style, and image quality.
The suite contains 80 stories and 344 characters. Scoring code changed character matching in December 2025, so comparisons must identify the code version.
- Released
- May 2025
- Kind
- Image generation and editing
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Image, video and 3D generation
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
In the authors’ words
Story visualization aims to generate coherent image sequences that faithfully represent a narrative and match given character references. Despite progress in generative models, existing benchmarks remain narrow in scope, often limited to short prompts, lacking character references, or single-image cases, failing to reflect real-world narrative complexity and obscuring true model performance.We introduce ViStoryBench, a comprehensive benchmark designed to evaluate story visualization models across varied narrative structures, visual styles, and character settings. It features richly annotated multi-shot scripts derived from curated stories spanning literature, film, and folklore. Large language models assist in story summarization and script generation, with all outputs verified by humans for coherence and fidelity. Character references are carefully curated to maintain consistency across different artistic styles. ViStoryBench proposes a suite of multi-dimensional automated metrics to evaluate character consistency, style similarity, prompt alignment, aesthetic quality, and artifacts like copy-paste behavior. These metrics are validated through human studies and used to assess a broad range of open-source and commercial models, enabling systematic analysis and encouraging advances in visual storytelling.
OmniGen2 tops the leaderboard with 1.00 Qwen-Image-Edit-2509 leads with 2.00
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The Full leaderboard reports overall rank across 80 stories. A lower rank is better. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen-Image-Edit-2509, at 2.00. This view shows only models we track, each at its best.
- 1 OmniGen2 Base 1.00
- 2
Qwen-Image-Edit-2509 Base 2.00
- 3 UNO Base 3.00
- 4 StoryDiffusion Original 4.00
- 5 StoryAdapter ImgRef_Scale0 5.00
- 6 MovieAgent SD3 7.00
- 7 AnimDirector SD3 8.00
- 8 CharaConsist Base 10.0
- 9 MMStoryAgent Base 12.0
- 10 TheaterGen Base 14.0
- 11 StoryGen AutoRegressive 15.0
- 12 Vlogger ImgRef 17.0
- 13 SEED-Story Base 21.0
Source: Official ViStoryBench leaderboard
- 1
Qwen-Image-Edit-2509 Base 2.00
Source: Official ViStoryBench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | OmniGen2 | 1.00 | Base | Official leaderboard | |
| 2 | | 2.00 | Base | Sep 2025 | Official leaderboard |
| 3 | UNO | 3.00 | Base | Official leaderboard | |
| 4 | StoryDiffusion | 4.00 | Original | Official leaderboard | |
| 5 | StoryAdapter | 5.00 | ImgRef_Scale0 | Official leaderboard | |
| 6 | MovieAgent | 7.00 | SD3 | Official leaderboard | |
| 7 | AnimDirector | 8.00 | SD3 | Official leaderboard | |
| 8 | CharaConsist | 10.0 | Base | Official leaderboard | |
| 9 | MMStoryAgent | 12.0 | Base | Official leaderboard | |
| 10 | TheaterGen | 14.0 | Base | Official leaderboard | |
| 11 | StoryGen | 15.0 | AutoRegressive | Official leaderboard | |
| 12 | Vlogger | 17.0 | ImgRef | Official leaderboard | |
| 13 | SEED-Story | 21.0 | Base | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 2.00 | Base | Sep 2025 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official ViStoryBench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Qwen-Image-Edit-2509. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (13 entries).
- Pass Models scored 1 model we track, plus 12 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for Qwen-Image-Edit-2509.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on vistorybench.github.io: 1 row for models we track and 12 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.