Image and video generation / Benchmark leaderboard
GenEval
Text-to-image compositional correctness: objects, counts, colors and spatial relations.
No published company result yet.
This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.
Arrange an evaluation for your company →What this benchmark measures
Metrics
Detector-based compositional success.
Execution requirements
Image generation API with fixed prompts, seeds and sample counts.
Scope and limitations
Useful for prompt adherence, not a complete aesthetic/typography score; detector limitations can affect results.
Evaluation availability
Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.
Sources and company fit
- Original benchmark ↗Established
Companies whose products may fit
Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.
Compatibility notes for each company
Adobe: Capability-aligned; adapter/access to qualify
Black Forest Labs: Capability-aligned; adapter/access to qualify
Canva: Capability-aligned; adapter/access to qualify
Google DeepMind: Capability-aligned; adapter/access to qualify
Ideogram: Capability-aligned; adapter/access to qualify
Midjourney: Capability-aligned; adapter/access to qualify
OpenAI: Capability-aligned; adapter/access to qualify
Stability AI: Capability-aligned; adapter/access to qualify