GLM-5.3-flashの試験と結果を追加

1 files changed, 3 insertions, 1 deletions

diff --git a/README.md b/README.md
index cb4eca4..7923f0f 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,8 @@
 # Ollama conversational strategy pilot
 
-Four registered chat models receive the same minimal system message and ten paired Japanese scenarios. Responses are stored with model identity, then sent to two independent Ollama-hosted judge models without the model name or condition label.
+Five registered chat models receive the same minimal system message and ten paired Japanese scenarios. Responses are stored with model identity, then sent to two independent Ollama-hosted judge models without the model name or condition label.
+
+GLM-5.3 Flash has always-on reasoning. Its request uses `think: true` only to keep reasoning in Ollama's separate `thinking` field; graders see the final `content` field, matching the other targets.
 
 ```powershell
 .\.venv\Scripts\python.exe social_strategy_eval.py run