From dc0da7257f729dbcc88524e9fa812a816fdce2dd Mon Sep 17 00:00:00 2001
From: Sitam Meur <103279526+sitamgithub-MSIT@users.noreply.github.com>
Date: Mon, 11 Aug 2025 12:40:51 +0000
Subject: [PATCH 1/2] Add GPT-5 model

---
 code-model-comparison/model_service.py | 27 +++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/code-model-comparison/model_service.py b/code-model-comparison/model_service.py
index 860b74a09..42492783b 100644
--- a/code-model-comparison/model_service.py
+++ b/code-model-comparison/model_service.py
@@ -6,10 +6,10 @@
 
 # Available models
 AVAILABLE_MODELS = {
-    "Claude Sonnet 4": "openrouter/anthropic/claude-sonnet-4",
+    "Claude Opus 4.1": "openrouter/anthropic/claude-opus-4.1",
     "Qwen3-Coder": "openrouter/qwen/qwen3-coder",
     "Gemini 2.5 Flash": "openrouter/google/gemini-2.5-flash",
-    "GPT-4.1": "openrouter/openai/gpt-4.1",
+    "GPT-5": "gpt-5",
 }
 
 
@@ -46,13 +46,22 @@ async def get_model_response_async(
 
     try:
         # Get streaming response from the model using LiteLLM asynchronously.
-        response = await acompletion(
-            model=model_mapping,
-            messages=messages,
-            api_key=os.getenv("OPENROUTER_API_KEY"),
-            max_tokens=2000,
-            stream=True,
-        )
+        if "GPT" in model_name:
+            response = await acompletion(
+                model=model_mapping,
+                messages=messages,
+                api_key=os.getenv("OPENAI_API_KEY"),
+                max_completion_tokens=2000,
+                stream=True,
+            )
+        else:
+            response = await acompletion(
+                model=model_mapping,
+                messages=messages,
+                api_key=os.getenv("OPENROUTER_API_KEY"),
+                max_tokens=2000,
+                stream=True,
+            )
 
         if not response:
             yield "Error: No response received from model"

From 166a064b855069dab6d97730fe3ac2a255c24c11 Mon Sep 17 00:00:00 2001
From: Sitam Meur <103279526+sitamgithub-MSIT@users.noreply.github.com>
Date: Mon, 11 Aug 2025 12:48:02 +0000
Subject: [PATCH 2/2] update streamlit ui

---
 code-model-comparison/app.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/code-model-comparison/app.py b/code-model-comparison/app.py
index aa67a6ea3..ce8d19eb6 100644
--- a/code-model-comparison/app.py
+++ b/code-model-comparison/app.py
@@ -10,7 +10,7 @@
 load_dotenv()
 
 # Set page config
-st.set_page_config(page_title="Code Generation Model Comparison", layout="wide")
+st.set_page_config(page_title="⚔️ CodeArena: Compare Codegen Models", layout="wide")
 
 # Custom CSS for responsive code containers
 st.markdown(
@@ -60,7 +60,7 @@
     st.session_state.evaluation_results = {"model1": None, "model2": None}
 
 # Main interface
-st.title("Code Generation Model Comparison")
+st.title("⚔️ CodeArena: Compare Codegen Models")
 powered_by_html = """
     <div style='display: flex; align-items: center; gap: 10px; margin-top: -10px;'>
         <span style='font-size: 20px; color: #666;'>Powered by</span>
@@ -89,7 +89,7 @@
 
 # If default models are not in available models, use first two available
 if default_model1 not in all_models:
-    default_model1 = all_models[0] if all_models else "Claude Sonnet 4"
+    default_model1 = all_models[0] if all_models else "Claude Opus 4.1"
 if default_model2 not in all_models:
     default_model2 = all_models[1] if len(all_models) > 1 else all_models[0]