From 76df3fef3cc59b9a7d8c52ff4c4b591a8bc25462 Mon Sep 17 00:00:00 2001
From: Nicolas Oulianov <58109554+oulianov@users.noreply.github.com>
Date: Wed, 20 Nov 2024 12:10:45 +0100
Subject: [PATCH] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 4db7bce..ae2569b 100644
--- a/README.md
+++ b/README.md
@@ -59,6 +59,8 @@ Each LLM has an ELO score based on its results.
 |   13 | **together:meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo:vision** | 1269.84 |
 |   14 | anthropic:claude-3-sonnet-20240229:text                            | 1029.31 |
 
+*Note: In our experiments, Claude 3 Sonnet got a low score due to many refusal to fight and large API latencies.*
+
 ### Win rate matrix
 
 ![Win rate matrix](notebooks/result_matrix.png)