Spaces:
No application file
No application file
Commit Β·
7544da4
1
Parent(s): aadf5fa
Add TrustModel organization card
Browse files
README.md
CHANGED
|
@@ -1,10 +1,70 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: blue
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
pinned: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: TrustModel
|
| 3 |
+
emoji: π‘οΈ
|
| 4 |
colorFrom: blue
|
| 5 |
+
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
pinned: false
|
| 8 |
+
tags:
|
| 9 |
+
- ai-safety
|
| 10 |
+
- ai-governance
|
| 11 |
+
- model-evaluation
|
| 12 |
+
- bias-detection
|
| 13 |
+
- red-teaming
|
| 14 |
---
|
| 15 |
|
| 16 |
+
# TrustModel
|
| 17 |
+
|
| 18 |
+
**Independent AI evaluation platform β validating, securing, and monitoring AI for enterprise trust.**
|
| 19 |
+
|
| 20 |
+
TrustModel evaluates AI systems across 10 trust dimensions using multi-judge consensus, producing regulator-ready compliance evidence for ISO 42001, NYC LL 144, NIST AI RMF, EU AI Act, and more.
|
| 21 |
+
|
| 22 |
+
## What We Evaluate
|
| 23 |
+
|
| 24 |
+
- **Foundation Models** β GPT, Claude, Gemini, Llama and more, ranked across 10 dimensions
|
| 25 |
+
- **Enterprise AI (COTS)** β Workday, SAP, Salesforce and 230+ systems
|
| 26 |
+
- **Browser Extensions** β Top 108 Chrome extensions scored for trust & safety
|
| 27 |
+
- **MCP Servers** β 91 MCP servers ranked for tool safety & risk
|
| 28 |
+
|
| 29 |
+
## Leaderboards
|
| 30 |
+
|
| 31 |
+
| Leaderboard | Link |
|
| 32 |
+
|-------------|------|
|
| 33 |
+
| Foundation Models | [trustmodel.ai/leaderboard](https://trustmodel.ai/leaderboard) |
|
| 34 |
+
| COTS / Enterprise Apps | [trustmodel.ai/benchmark](https://trustmodel.ai/benchmark) |
|
| 35 |
+
| Browser Extensions | [trustmodel.ai/chrome-extensions](https://trustmodel.ai/chrome-extensions) |
|
| 36 |
+
| MCP Servers | [trustmodel.ai/mcp-servers](https://trustmodel.ai/mcp-servers) |
|
| 37 |
+
|
| 38 |
+
## 10 Trust Dimensions
|
| 39 |
+
|
| 40 |
+
1. Accuracy
|
| 41 |
+
2. Hallucination
|
| 42 |
+
3. Bias & Safety
|
| 43 |
+
4. Reasoning
|
| 44 |
+
5. Instruction Adherence
|
| 45 |
+
6. Context Awareness
|
| 46 |
+
7. Enterprise Alignment
|
| 47 |
+
8. Security & Vulnerability
|
| 48 |
+
9. Operational
|
| 49 |
+
10. Specialization
|
| 50 |
+
|
| 51 |
+
## Compliance Frameworks
|
| 52 |
+
|
| 53 |
+
- [ISO/IEC 42001](https://trustmodel.ai/iso42001) β AI Management System
|
| 54 |
+
- [NYC Local Law 144](https://trustmodel.ai/nyc-ll144) β AEDT Bias Audits
|
| 55 |
+
- [Colorado AI Act](https://trustmodel.ai/colorado-ai-act) β SB24-205 Compliance
|
| 56 |
+
- NIST AI RMF β Risk Management Framework
|
| 57 |
+
- EU AI Act β High-Risk AI Compliance
|
| 58 |
+
|
| 59 |
+
## Add a TrustScore Badge to Your Model
|
| 60 |
+
|
| 61 |
+
```markdown
|
| 62 |
+
[](https://trustmodel.ai/leaderboard)
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
## Links
|
| 66 |
+
|
| 67 |
+
- **Website:** [trustmodel.ai](https://trustmodel.ai)
|
| 68 |
+
- **Documentation:** [trustmodel.ai/developers](https://trustmodel.ai/developers)
|
| 69 |
+
- **Methodology:** [trustmodel.ai/how-it-works](https://trustmodel.ai/how-it-works)
|
| 70 |
+
- **Contact:** [trustmodel.ai/contact](https://trustmodel.ai/contact)
|