Risk Index

Average of the risk and safety benchmarks published by the CAIS AI Dashboard; lower is better.

Metric

Average score (lower is better)

Results shown

Publisher

CAIS AI Dashboard

Snapshot

Fetched 2026-09-17T23:25:31.888Z

9 of 9 models

Lower is better

Fable 5.1

Muse Spark 1.1

GPT-6 Astra

Opus 5

GLM 5.3

Grok 4.5

Kimi K3

Gemini 3.1 Pro

DeepSeek 4 Pro

List bars visualize relative performance. Plot bars use published 0–100 scores, shrink to a 1.5rem minimum, then scroll horizontally.

Scores are published snapshots and are only comparable within the same benchmark, version, metric, and evaluation configuration.