diff --git a/docs/docs/benchmark.mdx b/docs/docs/benchmark.mdx
index 95016d8..e366193 100644
--- a/docs/docs/benchmark.mdx
+++ b/docs/docs/benchmark.mdx
@@ -30,6 +30,8 @@ Some of the LLMs above require using custom libraries to post-process LLM genera
 
 `Nexusflow/NexusRaven-V2-13B` required [nexusraven-pip](https://github.com/nexusflowai/nexusraven-pip).
 
+`functionary-small-v2.5` and `functionary-medium-v3.0` models are tested using [MeetKai's functionary](https://github.com/MeetKai/functionary?tab=readme-ov-file#setup) with the vllm framework. For each model, we compared the results with functionary's `Grammar Sampling` feature enabled and disabled, taking the highest score from either configuration. The `functionary-small-v2.5` model achieved a higher score than the `functionary-medium-v3.0` model, primarily due to the medium model exhibiting more hallucinations in some of our more advanced test cases.
+
 :::::
 
 ∔ `Nexusflow/NexusRaven-V2-13B` and `gorilla-llm/gorilla-openfunctions-v2` don't accept tool observations, the result of running a tool or function once the LLM calls it, so we appended the observation to the prompt.
\ No newline at end of file
diff --git a/docs/src/components/BenchmarkTable.js b/docs/src/components/BenchmarkTable.js
index 94f54ae..f2ee978 100644
--- a/docs/src/components/BenchmarkTable.js
+++ b/docs/src/components/BenchmarkTable.js
@@ -200,6 +200,26 @@ const data = [
         gsm8k: '-',
         math: '-',
         mtBench:'-',
+    },
+    {
+        model: 'functionary-medium-v3.0',
+        params: 70.6,
+        functionCalling: '46.43%',
+        mmlu: '79.85',
+        gpqa: '38.39',
+        gsm8k: '89.54',
+        math: '43.02',
+        mtBench:'5.49',
+    },
+    {
+        model: 'functionary-small-v2.5',
+        params: 8.03,
+        functionCalling: '57.14%',
+        mmlu: '63.92',
+        gpqa: '32.14',
+        gsm8k: '66.11',
+        math: '20.54',
+        mtBench:'7.09',
     }
 ];