Model Catalog Seed Reproducibility
fal · fal
Generative media inference — fal
Evaluates fal's Model Catalog Seed Reproducibility across 8 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Generative media inference eval coverage.
About fal
fal is a generative media inference platform offering fast, scalable image, video, and audio generation through a simple API. It hosts leading open models (FLUX, Stable Diffusion, Whisper) and supports fine-tuned LoRA routing, webhooks, and queue-based async generation at production scale.
Sample tests· showing 3 of 8
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | CI golden tests require model page id. | Use exact fal-ai/flux/schnell string from config; reject aliases. | Pass / FailWorkflowhigh |
| 02 | Typo fal-ai/flux/schnl on submit. | Catch 404; user message; no retry loop. | Pass / FailWorkflowmedium |
| 03 | QA regression on flux schnell. | Two identical subscribe calls; hash compare; flag drift. | Pass / FailWorkflowhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric.
Rubric criteria
- Fal
- Ai Platform
- Model Catalog Seed Reproducibility
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Model Catalog Seed Reproducibility eval for fal fal test?+
Evaluates fal's Model Catalog Seed Reproducibility across 8 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Generative media inference eval coverage.
How is the Model Catalog Seed Reproducibility eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric.
How many test cases does this eval pack include?+
The Model Catalog Seed Reproducibility pack for fal fal contains 8 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Model Catalog Seed Reproducibility pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.