CAIS Risk Index — leaderboard
Composite CAIS AI Dashboard risk index averaging VCT refusal risk, HLE miscalibration, MASK risk, Machiavelli, and TextQuests Harm for models with all component scores. Lower is better.
Metric: Risk Index (self-reported). Source: benchmarklist.com. 37 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-11-20) | 67 |
| 2 | Gemini 2.5 Flash Lite | 66.4 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 61.7 |
| 4 | Gemini 2.5 Flash | 60.1 |
| 5 | O3 Mini (High) | 60.1 |
| 6 | Gemini 3 Flash (Preview) | 59.4 |
| 7 | Gemini 2.5 Pro | 59 |
| 8 | Gemini 3.5 Flash | 58.2 |
| 9 | Kimi K2 (Thinking) | 57.4 |
| 10 | DeepSeek V3.2 | 56.9 |
| 11 | Gemini 3.1 Pro (Preview) | 55.6 |
| 12 | Grok 4 Fast | 55.3 |
| 13 | DeepSeek V4 Pro | 54.1 |
| 14 | Grok 4.1 Fast | 52.2 |
| 15 | GPT-5 Nano | 51.9 |
Interactive version: theaggregate.ai/benchmark?slug=cais-risk-index · How the rankings work · Data refreshed daily, snapshot 2026-07-22.