Deployments
Replicate · Replicate
AI Model Hosting — Replicate
Evaluates Replicate's Deployments across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Model Hosting eval coverage.
About Replicate
Replicate is an AI model-hosting platform — run thousands of community and custom Cog-packaged models (FLUX, SDXL, Llama, Whisper, custom fine-tunes) via a simple HTTP API with predictions, webhooks, streaming, deployments, and per-second billing.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Operator runs a customer-facing FLUX deployment with min_replicas=0 to save cost. First request after 10 minutes idle takes 30 s instead of 2 s. | min_replicas=0 enables scale-to-zero, trading cold-start latency for idle cost. For low-latency UX, set min_replicas>=1 during business hours (scheduled) or accept the cold-start budget. Per-tier cold-start latency [REQUIRES-VERIFICATION] — measure on the chosen hardware. | Pass / FailAi Platformcritical |
| 02 | Deployment with max_replicas=4 receives a burst of 200 concurrent requests; the 5th-200th queue. | Autoscaling scales up to max_replicas. Excess concurrent requests queue on the deployment. Tune max_replicas to absorb peak burst within an acceptable p95 latency. Above max_replicas, latency degrades — monitor queue depth as the leading indicator. | Pass / FailAi Platformhigh |
| 03 | Operator creates a deployment with hardware='gpu-h100-large' for an SDXL model that runs fine on A40. | Match hardware to the model's documented requirement. H100 for an A40 workload over-pays per second. Run a hardware bake-off on a representative load before committing. Document the chosen tier and rerun bake-off on version upgrades. | Pass / FailAi Platformhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Replicate
- Ai Platform
- Deployments
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 Deployments eval for Replicate Replicate test?+
Evaluates Replicate's Deployments across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Model Hosting eval coverage.
How is the Deployments eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Deployments pack for Replicate Replicate contains 9 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 Deployments 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.