From 2e31c6013d3a5ea3feb4a17110a96db098559b93 Mon Sep 17 00:00:00 2001
From: wassname <1103714+wassname@users.noreply.github.com>
Date: Tue, 28 Jul 2026 21:54:11 +0800
Subject: [PATCH] Show the four explanation-model capability scores

---
 README.md | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/README.md b/README.md
index 46971b4..e4996d9 100644
--- a/README.md
+++ b/README.md
@@ -21,6 +21,13 @@ For each scene, we chose the actions with the lowest and highest MACHIAVELLI
 harm annotation totals. Each of four Qwen 3.5 models explained both actions
 under the two motive instructions shown above.
 
+| explanation model | [Artificial Analysis score](https://artificialanalysis.ai/?models=qwen3-5-9b%2Cqwen3-5-27b%2Cqwen3-5-397b-a17b%2Cqwen3-5-122b-a10b%2Cqwen3-5-35b-a3b) |
+|:--|--:|
+| Qwen 3.5 9B | 21 |
+| Qwen 3.5 35B-A3B | 29 |
+| Qwen 3.5 122B-A10B | 32 |
+| Qwen 3.5 397B-A17B | 34 |
+
 The Hugging Face dataset card explains the two configurations, intended uses,
 columns, QA flags, and limitations.