add groq tool use models benchmark (#134)

docs/docs/benchmark.mdx

@@ -32,6 +32,8 @@ Some of the LLMs above require using custom libraries to post-process LLM genera
 
 `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.
 
+`groq/Llama-3-Groq-8B-Tool-Use` and `groq/Llama-3-Groq-70B-Tool-Use` are tested using [groq's API](https://console.groq.com/docs/tool-use).
+
 :::::
 
 ∔ `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.

docs/src/components/BenchmarkTable.js

@@ -229,6 +229,26 @@ const data = [
         gsm8k: '66.11',
         math: '20.54',
         mtBench:'7.09',
+    },
+    {
+        model: 'groq/Llama-3-Groq-8B-Tool-Use',
+        params: 8.03,
+        functionCalling: '45.70%',
+        mmlu: '-',
+        gpqa: '-',
+        gsm8k: '-',
+        math: '-',
+        mtBench:'-',
+    },
+    {
+        model: 'groq/Llama-3-Groq-70B-Tool-Use',
+        params: 70.6,
+        functionCalling: '74.29%',
+        mmlu: '-',
+        gpqa: '-',
+        gsm8k: '-',
+        math: '-',
+        mtBench:'-',
     }
 ];