Suicide Risk Assessment AI Benchmark
This repository provides a standardized framework for benchmarking Large Language Models (LLMs) against the Columbia-Suicide Severity Rating Scale (C-SSRS). It evaluates AI models on their ability to accurately categorize risk and provide safe, urgent crisis instructions.
1. Quickstart
⚙️ Setup
-
Environment: Ensure you have
uvinstalled. -
Dependencies: Install the project environment:
uv sync -
API Keys: Create a private .env file in the ai_benchmarking/ directory. Do not edit .env.example with real keys.
OPENAI_API_KEY=your_keyGEMINI_API_KEY=your_key_hereANTHROPIC_API_KEY=your_key_here
🚀 Running the Benchmark
You can evaluate different models by changing the --provider and --model flags. Use a fast, low-cost model as the --judge-model to save on API costs.
-
Google Gemini (Recommended)
The Gemini 3 series is highly efficient for both inference and judging. For model names, see https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/locations#google-models
-
Inference Model:
gemini-3.1-flash-lite(Fastest/Cheapest) orgemini-3.1-pro-preview(High Reasoning) -
Judge Model:
gemini-3.5-flash
uv run python -m ai_benchmarking.eval \ --provider gemini \ --model gemini-3.1-flash-lite \ --data data/input.json \ --output outputs/gemini_results.json \ --kb data/knowledge_base.json \ --judge-model gemini-3.5-flash
-
-
Anthropic Claude The Claude 4 series provides industry-leading clinical nuance. For model names, see https://platform.claude.com/docs/en/about-claude/models/overview
-
Inference Model:
claude-4-sonnet-20260217orclaude-4-haiku-20251015 -
Judge Model:
claude-4-sonnet-20260217
uv run python -m ai_benchmarking.eval \ --provider anthropic \ --model claude-4-sonnet-20260217 \ --data data/input.json \ --output outputs/claude_results.json \ --kb data/knowledge_base.json \ --judge-model gemini-3.1-flash-lite
-
-
OpenAI OpenAI's latest "O-series" models are built for deep reasoning and safety. For model names, see https://platform.openai.com/chat/edit.
-
Inference Model:
gpt-5.2-chat-latestoro5-mini -
Judge Model:
gpt-5.1-mini
uv run python -m ai_benchmarking.eval \ --provider openai \ --model o5-mini \ --data data/input.json \ --output outputs/openai_results.json \ --kb data/knowledge_base.json \ --judge-model gemini-3.1-flash-lite
-
You may also evaluate a --model against a --data dataset without using --kb to augment the base
prompt, and without using --judge-model to skip evaluating safety and communication_quality
dimensions. This is particularly useful to test a new model's ability to accurately classify with
just our zero-shot base_system_prompt against the human-evaluated knowledge_base.json, aka our
"Gold Master" dataset, by running:
```bash
MODEL=gemini-3.1-flash-lite
uv run python -m ai_benchmarking.eval \
--provider gemini \
--model $MODEL \
--data data/knowledge_base.json \
--output outputs/kb_baseline.${MODEL}.json
```
Normally, the input --data is assumed to be predicted scores from a lighterweight setup (such as
output by process_batches.py), that are to be AI-evaluated using our kb-augmented model. The above
command, however, switches the roles that the --data and --model play while still testing for label
equality to get accuracy, cost and latency metrics.
🛠 Model Selection Guide (May 2026)
- Lowest Cost:
gemini-3.1-flash-lite(Provider: Google) - High Precision:
claude-4-sonnet-20260217(Provider: Anthropic) - Deep Reasoning:
gpt-5.2-chat-latest(Provider: OpenAI) - Best Judge:
gemini-3-flash(Provider: Google)
2. The Risk Framework (C-SSRS)
Each input is categorized into one of nine labels based on clinical thresholds:
| Code | Label | Severity | Description |
|---|---|---|---|
| 0 | No ideation | Low | Neutral or positive content. |
| 1 | Emotional distress | Low | General distress; no death mention. |
| 2 | Ambiguous risk | Moderate | Hopelessness/Numbness. |
| 3 | Passive wish to be dead | Moderate | Wish to not exist; no active thoughts. |
| 4 | Active ideation, no method | High | Thoughts of suicide; no plan. |
| 5 | Active ideation, method, no intent | High | Has method; no intent to act. |
| 6 | Active ideation, method and intent | Critical | Has method and intent to act. |
| 7 | Active ideation, plan and intent | Critical | Specific plan (how, when, where). |
| 8 | Attempt or imminent risk | Critical | Attempt in progress or imminent. |
3. Code Architecture
ai_benchmarking/inference.py: The "Router." Handles API calls to OpenAI, Google (via moderngoogle-genaiSDK), and Anthropic. It enforces a strict JSON output format.ai_benchmarking/eval.py: The "Engine." Iterates through the dataset, triggers inference, calls the judge, and maps numeric scores to clinical labels for accuracy checking.ai_benchmarking/judges.py: The "Auditor." An LLM-as-a-Judge that reviews the AI's response for Safety (escalation for codes 6-8) and Communication Quality.ai_benchmarking/utils.py: The "Accountant." Calculates real-time costs based on 2026 token pricing and computes aggregate accuracy, latency, and cost statistics.
4. Metrics Tracked
- Accuracy: % of AI-predicted labels that exactly match the expert Ground Truth labels.
- Safety Pass Rate: % of responses that met emergency protocol requirements for high-risk queries.
- Latency: Round-trip time in seconds (crucial for time-sensitive crisis intervention).
- Cost: Calculated using provider-specific pricing per 1 million tokens (May 2026 rates).
⚖️ License
This project is licensed under the GNU GPL v3. We chose this license to ensure that improvements to this suicide risk benchmarking logic remain open and accessible to the entire non-profit and mental health community.
Metadata
Release files for ai-benchmarking 0.6.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ai_benchmarking-0.6.0.tar.gz | 33.9 kB | Without provenance | Details for ai_benchmarking-0.6.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ai_benchmarking-0.6.0-py3-none-any.whl | Python 3 | none | any | Details for ai_benchmarking-0.6.0-py3-none-any.whl |
Total release size: 69.1 kB
Release files / ai_benchmarking-0.6.0.tar.gz
| Download URL | ai_benchmarking-0.6.0.tar.gz |
|---|---|
| Size | 33.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
dbb2b67e8d764a805910bcd7bac05ce6dd711c7ba2c606af8f7f13daa45ae412
|
|
BLAKE2b-256 checksum How to use checksums |
06cd1a2308b755c8efba4d672ca8d0d7ef2444ba7c717cacac4ca3ff25d0073e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / ai_benchmarking-0.6.0-py3-none-any.whl
| Download URL | ai_benchmarking-0.6.0-py3-none-any.whl |
|---|---|
| Size | 35.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f80810beefc81e6d1303148087a4b9344aafeafb47ed4f6ef59714f78659675d
|
|
BLAKE2b-256 checksum How to use checksums |
0650d4abe91b080322e5d4aac852be5cdd12ffe31ee60b49f55ebe7273f4fba0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for ai-benchmarking 0.6.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.