diff --git a/requirements-dev.txt b/requirements-dev.txt
index 9be7f3913..13864a0c6 100644
--- a/requirements-dev.txt
+++ b/requirements-dev.txt
@@ -5,7 +5,7 @@ openai
 pytest >= 6.0
 pytest-asyncio
 pytest-mock
-lm-eval==0.4.8
+lm-eval[api] @ git+https://github.com/EleutherAI/lm-evaluation-harness.git@206b7722158f58c35b7ffcd53b035fdbdda5126d 
 types-jsonschema
 xgrammar
 zmq