Review & score
Judge whether a model's answer to a case is safe.
Datasets
The prompt library — import from any source, then run or cherry-pick it from any engine.
| Dataset | Source | Origin | Cases | Added by |
|---|
Import garak probes → datasets
Pull garak attack prompts into source: garak datasets. Search all 189, tick one or more — each becomes its own dataset.
Import Inspect tasks → datasets
Borrow Inspect benchmark questions into source: inspect datasets. Search all tasks, tick one or more — each becomes its own dataset. For the official result, run the Inspect kind on the Runs page.
Import a dataset
Coverage
What's assessed, mapped to the 4 building blocks and 8 safety dimensions. Status is computed from completed runs.
The 4 building blocks
| Block | How it runs here | Status |
|---|
The 8 safety dimensions
| Dimension | Risk | Scored cases | Pass | Evidence | Status |
|---|
Leaderboard
Every run and its results. Generate an Assurance Report from any row.
| Run | Target (receiver) | Attacker | Grader model | Human reviewers | Auto pass | Human ✓/✗/? |
|---|
Runs
Run a model under test; results feed scoring, coverage and reports.
New run
| Run | Target | Attacker | Grader | Progress | Auto-grade |
|---|
Users
Create accounts and reset passwords.
Add user
| User | Role | Status | Permissions |
|---|
Model providers
Connect target, attacker and grader models by API.
Add provider
Which kind do I pick?
openai-compatible is the catch-all — Gemini, Qwen, DeepSeek, Mistral, Grok and most others expose an OpenAI-style endpoint. Anthropic and local Ollama have dedicated kinds.
| Model | Kind | Base URL | Example model id |
|---|---|---|---|
| OpenAI | openai-compatible | https://api.openai.com/v1 | gpt-4o |
| Google Gemini | openai-compatible | https://generativelanguage.googleapis.com/v1beta/openai/ | gemini-2.5-pro |
| Qwen (Alibaba DashScope) | openai-compatible | https://dashscope-intl.aliyuncs.com/compatible-mode/v1 | qwen-max |
| DeepSeek | openai-compatible | https://api.deepseek.com | deepseek-chat |
| Mistral | openai-compatible | https://api.mistral.ai/v1 | mistral-large-latest |
| xAI Grok | openai-compatible | https://api.x.ai/v1 | grok-2 |
| OpenRouter (one key → most models) | openai-compatible | https://openrouter.ai/api/v1 | google/gemini-2.5-pro |
| Anthropic Claude | anthropic | — not needed — | claude-opus-4-8 |
| Local (Ollama / vLLM / LM Studio) | ollama or openai-compatible | http://localhost:11434 · /v1 | gemma4-assurance |
If a model has no OpenAI-compatible endpoint, route it through OpenRouter.
| Label | Kind | Model | Status |
|---|
My account
Your sign-in details and password.
Change password
App settings
Owner only. Brand and theme the platform — changes apply to everyone instantly.
Branding
Theme
Two colours drive the whole UI — accent and the navigation rail.