diff --git a/.gitattributes b/.gitattributes
index 5eb15f71d2fdf21bd2a2723b48a1d36b9d338cad..09112527a34ed84f21a9236bef3274bb30304f5a 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -284,3 +284,53 @@ results/gpt-4-1106.pkl filter=lfs diff=lfs merge=lfs -text
 results/Llama-3-70b-chat-hf.pkl filter=lfs diff=lfs merge=lfs -text
 results/dbrx-instruct.pkl filter=lfs diff=lfs merge=lfs -text
 results/gpt-3.5-0613.pkl filter=lfs diff=lfs merge=lfs -text
+final_df.pkl filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-haiku-20240307_vision.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Mixtral-8x7B-Instruct-v0.1_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-haiku-20240307_vision-CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-1106_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-vision-preview_vision-CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/dbrx-instruct_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Llama-2-70b-chat-hf_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Llama-3-70b-chat-hf_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Llama-3-70b-chat-hf_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Mistral-7B-Instruct-v0.2_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-sonnet-20240229_vision.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/CodeLlama-70b-Instruct-hf_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-haiku-20240307_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gemma-7b-it_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-0125-preview_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-haiku-20240307_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Mistral-7B-Instruct-v0.2_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Qwen1.5-72B-Chat_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-3.5-turbo-0125_1shot.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-sonnet-20240229_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Mixtral-8x7B-Instruct-v0.1_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gemma-7b-it_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-0125-preview_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-turbo-2024-04-09_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-haiku-20240307_1shot.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-opus-20240229_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/deepseek-llm-67b-chat_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-opus-20240229_vision-CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gemini-pro_vision-CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-3.5-0613_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-vision-preview_vision.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gemini-pro_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/CodeLlama-70b-Instruct-hf_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Qwen1.5-72B-Chat_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Yi-34B-Chat_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-sonnet-20240229_vision-CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/dbrx-instruct_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gemini-pro_vision.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-3.5-0613_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-1106_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-4-turbo-2024-04-09_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Llama-2-70b-chat-hf_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-opus-20240229_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-3.5-turbo-0125_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/gpt-3.5-turbo-0125_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/Yi-34B-Chat_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-opus-20240229_vision.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/claude-3-sonnet-20240229_CoT.jpg filter=lfs diff=lfs merge=lfs -text
+heatmaps/deepseek-llm-67b-chat_Textonly.jpg filter=lfs diff=lfs merge=lfs -text
diff --git a/app.py b/app.py
index 50ffb582c4cb951969e7103666620acf41a74540..58cfe4e5fd003b5fadaed2c63e96d7ca48907551 100644
--- a/app.py
+++ b/app.py
@@ -7,27 +7,50 @@ import pandas as pd
 import seaborn as sns
 from matplotlib.colors import BoundaryNorm, ListedColormap
 
-all_results = pd.read_pickle("all_results.pkl")
+all_results = pd.read_pickle("final_df.pkl")
 
 
-def get_accuracy_dataframe(df):
+def get_accuracy_dataframe(df_mother, category):
     # Calculate overall model accuracy
-    df['parsed_judge_response'] = df['parsed_judge_response'].astype(float)
-    model_accuracy = df.groupby('model_name')['parsed_judge_response'].mean().reset_index()
-    
+    # filter for category only
+    df = df_mother[df_mother["category"] == category].copy()
+    df["is_answer_correct"] = df["is_answer_correct"].astype(float)
+    model_accuracy = df.groupby("model")["is_answer_correct"].mean().reset_index()
+
     # Calculate model accuracy per difficulty level
-    df['difficulty_level'] = df['difficulty_level'].astype(int)
-    model_accuracy_per_level = df.groupby(['model_name', 'difficulty_level'])['parsed_judge_response'].mean().reset_index()
-    model_accuracy_per_level_df = model_accuracy_per_level.pivot(index='model_name', columns='difficulty_level', values='parsed_judge_response')
-    
+    df["difficulty_level"] = df["difficulty_level"].astype(int)
+    model_accuracy_per_level = (
+        df.groupby(["model", "difficulty_level"])["is_answer_correct"]
+        .mean()
+        .reset_index()
+    )
+    model_accuracy_per_level_df = model_accuracy_per_level.pivot(
+        index="model", columns="difficulty_level", values="is_answer_correct"
+    )
+
     # Merge overall accuracy and level-based accuracy into a single DataFrame
-    model_accuracy_df = model_accuracy.merge(model_accuracy_per_level_df, on='model_name')
-    model_accuracy_df.rename(columns={1: 'level_1', 2: 'level_2', 3: 'level_3', 4: 'level_4', 5: 'level_5'}, inplace=True)
-    model_accuracy_df.rename(columns={'parsed_judge_response': 'Accuracy'}, inplace=True)
-    
+    model_accuracy_df = model_accuracy.merge(model_accuracy_per_level_df, on="model")
+    model_accuracy_df.rename(
+        columns={"is_answer_correct": "Overall Accuracy"}, inplace=True
+    )
+
+    # Ensure all expected difficulty levels are present
+    expected_levels = [1, 2, 3, 4]  # Adjust based on your data
+    for level in expected_levels:
+        if level not in model_accuracy_df.columns:
+            model_accuracy_df[
+                level
+            ] = None  # Fill missing levels with None or an appropriate value
+
+    # Rename columns to include levels
+    level_columns = {level: f"Level {level} Accuracy" for level in expected_levels}
+    model_accuracy_df.rename(columns=level_columns, inplace=True)
+
     # Multiply by 100 and format to one decimal point
-    model_accuracy_df = model_accuracy_df.applymap(lambda x: round(x * 100, 1) if isinstance(x, float) else x)
-    
+    model_accuracy_df = model_accuracy_df.applymap(
+        lambda x: round(x * 100, 1) if isinstance(x, float) else x
+    )
+
     # Add headers with icons
     model_accuracy_df.columns = [
         "🤖 Model Name",
@@ -40,13 +63,15 @@ def get_accuracy_dataframe(df):
 
     model_accuracy_df.sort_values(by="⭐ Overall", ascending=False, inplace=True)
     
-    # Add a new column at the beginning for the rank
-    model_accuracy_df.insert(0, '#', range(1, len(model_accuracy_df) + 1))
-    
     return model_accuracy_df
 
 
-accuracy_df = get_accuracy_dataframe(all_results)
+# categories = array(['1shot', 'CoT', 'Textonly', 'vision', 'vision-CoT'], dtype=object)
+accuracy_df_textonly = get_accuracy_dataframe(all_results, "Textonly")
+accuracy_df_cot = get_accuracy_dataframe(all_results, "CoT")
+accuracy_df_vision = get_accuracy_dataframe(all_results, "vision")
+accuracy_df_vision_cot = get_accuracy_dataframe(all_results, "vision-CoT")
+accuracy_df_1shot = get_accuracy_dataframe(all_results, "1shot")
 
 
 # Define the column names with icons
@@ -68,126 +93,83 @@ column_names = [
     "Level 4 Accuracy",
 ]
 
-def load_heatmap(evt: gr.SelectData):
-    heatmap_image = gr.Image(f"results/{evt.value}.jpg")
+
+def load_heatmap_textonly(evt: gr.SelectData):
+    print(f"./heatmaps/{evt.value}_Textonly.jpg")
+    heatmap_image = gr.Image(f"./heatmaps/{evt.value}_Textonly.jpg")
     return heatmap_image
 
 
+def load_heatmap_cot(evt: gr.SelectData):
+    heatmap_image = gr.Image(f"./heatmaps/{evt.value}_CoT.jpg")
+    return heatmap_image
 
-# # Function to process data
-# def process_data(data):
-#     data_for_df = []
-#     for file, df in data.items():
-#         overall_accuracy = round(calculate_accuracy(df), 2)
-#         breakdown_accuracy = [round(acc, 2) for acc in accuracy_breakdown(df)]
-#         model_name = file.split("/")[-1].replace(".pkl", "")
-#         data_for_df.append([model_name, overall_accuracy] + breakdown_accuracy)
-#     return data_for_df
 
+def load_heatmap_vision(evt: gr.SelectData):
+    heatmap_image = gr.Image(f"./heatmaps/{evt.value}_vision.jpg")
+    return heatmap_image
 
-# # Function to finalize DataFrame
-# def finalize_df(df):
-#     df = df.round(1)  # Round to one decimal place
-#     df = df.applymap(lambda x: f"{x:.1f}" if isinstance(x, (int, float)) else x)
-#     df.columns = headers_with_icons
-#     df.sort_values(by="⭐ Overall", ascending=False, inplace=True)
-#     # add a new column with the order (index)
-#     df["#"] = range(1, len(df) + 1)
-#     # bring rank to the first column
-#     cols = df.columns.tolist()
-#     cols = cols[-1:] + cols[:-1]
-#     df = df[cols]
 
-#     return df
+def load_heatmap_vision_cot(evt: gr.SelectData):
+    heatmap_image = gr.Image(f"./heatmaps/{evt.value}_vision-CoT.jpg")
+    return heatmap_image
 
 
-def load_heatmap(evt: gr.SelectData):
-    heatmap_image = gr.Image(f"results/{evt.value}.jpg")
+def load_heatmap_1shot(evt: gr.SelectData):
+    heatmap_image = gr.Image(f"./heatmaps/{evt.value}_1shot.jpg")
     return heatmap_image
 
 
+# Then, use these functions in the corresponding select method calls:
+
 with gr.Blocks() as demo:
     gr.Markdown("# FSM Benchmark Leaderboard")
+
+    # Text-only Benchmark
     with gr.Tab("Text-only Benchmark"):
-        leader_board = gr.Dataframe(accuracy_df, headers=headers_with_icons)
+        leader_board_textonly = gr.Dataframe(
+            accuracy_df_textonly, headers=headers_with_icons
+        )
+        gr.Markdown("## Heatmap")
+        heatmap_image_textonly = gr.Image(label="", show_label=False)
+        leader_board_textonly.select(
+            fn=load_heatmap_textonly, outputs=[heatmap_image_textonly]
+        )
+
+    # CoT Benchmark
+    with gr.Tab("CoT Benchmark"):
+        leader_board_cot = gr.Dataframe(accuracy_df_cot, headers=headers_with_icons)
+        gr.Markdown("## Heatmap")
+        heatmap_image_cot = gr.Image(label="", show_label=False)
+        leader_board_cot.select(fn=load_heatmap_cot, outputs=[heatmap_image_cot])
+
+    # Vision Benchmark
+    with gr.Tab("Vision Benchmark"):
+        leader_board_vision = gr.Dataframe(
+            accuracy_df_vision, headers=headers_with_icons
+        )
+        gr.Markdown("## Heatmap")
+        heatmap_image_vision = gr.Image(label="", show_label=False)
+        leader_board_vision.select(
+            fn=load_heatmap_vision, outputs=[heatmap_image_vision]
+        )
+
+    # Vision-CoT Benchmark
+    with gr.Tab("Vision-CoT Benchmark"):
+        leader_board_vision_cot = gr.Dataframe(
+            accuracy_df_vision_cot, headers=headers_with_icons
+        )
+        gr.Markdown("## Heatmap")
+        heatmap_image_vision_cot = gr.Image(label="", show_label=False)
+        leader_board_vision_cot.select(
+            fn=load_heatmap_vision_cot, outputs=[heatmap_image_vision_cot]
+        )
+
+    # 1shot Benchmark
+    with gr.Tab("1shot Benchmark"):
+        leader_board_1shot = gr.Dataframe(accuracy_df_1shot, headers=headers_with_icons)
         gr.Markdown("## Heatmap")
-        heatmap_image_qwen = gr.Image(label="", show_label=False)
-        leader_board.select(fn=load_heatmap, outputs=[heatmap_image_qwen])
-
-    # with gr.Tab("Vision Benchmark", visible=False):
-    #     gr.Markdown("# Vision Benchmark Leaderboard")
-    #     leader_board_vision = gr.Dataframe(
-    #         vision_accuracy_df, headers=headers_with_icons
-    #     )
-    #     gr.Markdown("## Heatmap")
-    #     heatmap_image_vision = gr.Image(label="", show_label=False)
-    #     leader_board_vision.select(
-    #         fn=load_vision_heatmap, outputs=[heatmap_image_vision]
-    #     )
-
-    # with gr.Tab("Text-only Benchmark (CoT)", visible=False):
-    #     gr.Markdown("# Text-only Leaderboard (CoT)")
-    #     cot_leader_board_text = gr.Dataframe(
-    #         cot_text_accuracy_df, headers=headers_with_icons
-    #     )
-    #     gr.Markdown("## Heatmap")
-    #     cot_heatmap_image_text = gr.Image(label="", show_label=False)
-    #     cot_leader_board_text.select(
-    #         fn=load_cot_heatmap, outputs=[cot_heatmap_image_text]
-    #     )
-
-    # with gr.Tab("Constraint Text-only Results (CoT)", visible=False):
-    #     gr.Markdown("## Constraint Text-only Leaderboard by first substrin (CoT)")
-    #     included_models_cot = gr.CheckboxGroup(
-    #         label="Models to include",
-    #         choices=all_cot_text_only_models,
-    #         value=all_cot_text_only_models,
-    #         interactive=True,
-    #     )
-    #     with gr.Row():
-    #         number_of_queries_cot = gr.Textbox(label="Number of included queries")
-    #         number_of_fsms_cot = gr.Textbox(label="Number of included  FSMs")
-
-    #     constrained_leader_board_text_cot = gr.Dataframe()
-    #     constrained_leader_board_plot_cot = gr.Plot()
-
-    # with gr.Tab("Majority Vote (Subset 1)", visible=False):
-    #     gr.Markdown("## Majority Vote (Subset 1)")
-    #     intersection_leader_board = gr.Dataframe(
-    #         intersection_df_acc, headers=headers_with_icons
-    #     )
-    #     heatmap_image = gr.Plot(label="Model Heatmap")
-
-    # with gr.Tab("Text-only Benchmark (deprecated)", visible=False):
-    #     gr.Markdown("# Text-only Leaderboard")
-    #     leader_board = gr.Dataframe(accuracy_df, headers=headers_with_icons)
-    #     gr.Markdown("## Heatmap")
-    #     heatmap_image = gr.Image(label="", show_label=False)
-    #     leader_board.select(fn=load_heatmap, outputs=[heatmap_image])
-
-    # # ============ Callbacks ============
-
-    # included_models_cot.select(
-    #     fn=calculate_order_by_first_substring_cot,
-    #     inputs=[included_models_cot],
-    #     outputs=[
-    #         constrained_leader_board_text_cot,
-    #         number_of_queries_cot,
-    #         number_of_fsms_cot,
-    #     ],
-    #     queue=True,
-    # )
-
-    # constrained_leader_board_text.select(
-    #     fn=show_constraint_heatmap, outputs=[constrained_leader_board_plot]
-    # )
-
-    # constrained_leader_board_text_cot.select(
-    #     fn=show_constraint_heatmap_cot, outputs=[constrained_leader_board_plot_cot]
-    # )
-
-    # intersection_leader_board.select(
-    #     fn=show_intersection_heatmap, outputs=[heatmap_image]
-    # )
+        heatmap_image_1shot = gr.Image(label="", show_label=False)
+        leader_board_1shot.select(fn=load_heatmap_1shot, outputs=[heatmap_image_1shot])
 
     demo.launch()
diff --git a/heatmaps/CodeLlama-70b-Instruct-hf_CoT.jpg b/heatmaps/CodeLlama-70b-Instruct-hf_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..4ea4615e1955db222b675530bed773b17d22741e
--- /dev/null
+++ b/heatmaps/CodeLlama-70b-Instruct-hf_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5562512828afa9d7380b45e03211d71f3fdc84abf261bc5efb8d7420b892c15
+size 1317272
diff --git a/heatmaps/CodeLlama-70b-Instruct-hf_Textonly.jpg b/heatmaps/CodeLlama-70b-Instruct-hf_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..aa223f05698499aea107664f1c308e1661673b2e
--- /dev/null
+++ b/heatmaps/CodeLlama-70b-Instruct-hf_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0037755acca2e516f2c1ecb09eb046f93e85d7a9cd605bf57b9a2da924e87cef
+size 1323230
diff --git a/heatmaps/Llama-2-70b-chat-hf_CoT.jpg b/heatmaps/Llama-2-70b-chat-hf_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..49518c2d3666428b9e5bb2dc261db5163900f50f
--- /dev/null
+++ b/heatmaps/Llama-2-70b-chat-hf_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65e66abdce858dcf489b517d9cb30d9efe2f49175223e59eb1bf00d3b0bd6bd
+size 1332953
diff --git a/heatmaps/Llama-2-70b-chat-hf_Textonly.jpg b/heatmaps/Llama-2-70b-chat-hf_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a168d308057cedce51b08aa9f8cc60b64815a91c
--- /dev/null
+++ b/heatmaps/Llama-2-70b-chat-hf_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d993d8e78bd8fbb8db88071690771b6d483ae8a9bd7d043780623fb7a0267961
+size 1326224
diff --git a/heatmaps/Llama-3-70b-chat-hf_CoT.jpg b/heatmaps/Llama-3-70b-chat-hf_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..5a1ba5ddad82870bbdb7aef99239833d6fb10f3c
--- /dev/null
+++ b/heatmaps/Llama-3-70b-chat-hf_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e4e0dbdb6ecf372246158de9708088ce189d420c3cb7e8e101565802209833
+size 1277414
diff --git a/heatmaps/Llama-3-70b-chat-hf_Textonly.jpg b/heatmaps/Llama-3-70b-chat-hf_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..5edee483fba625673d1a2243b23ab2683f509a0b
--- /dev/null
+++ b/heatmaps/Llama-3-70b-chat-hf_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255d9bb5c182e5947463e7cec5bea78d8aef3b038bb74fa400aaa2c2d7cbe02a
+size 1288158
diff --git a/heatmaps/Mistral-7B-Instruct-v0.2_CoT.jpg b/heatmaps/Mistral-7B-Instruct-v0.2_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..ed002a91262bb211086367c931af805b344833ed
--- /dev/null
+++ b/heatmaps/Mistral-7B-Instruct-v0.2_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cedc95db3dfedb187d1c690cb5d78a08547f083e276cf3c4946a9dab8d2fb9
+size 1322691
diff --git a/heatmaps/Mistral-7B-Instruct-v0.2_Textonly.jpg b/heatmaps/Mistral-7B-Instruct-v0.2_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..100ec997d5835e12f8d4097482d37a27f555ef3c
--- /dev/null
+++ b/heatmaps/Mistral-7B-Instruct-v0.2_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cfc569d1baca9826b010eeb90af43b0077ea533d7fc8c1ae494671b255cdf1f
+size 1324535
diff --git a/heatmaps/Mixtral-8x7B-Instruct-v0.1_CoT.jpg b/heatmaps/Mixtral-8x7B-Instruct-v0.1_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..ca1ce97a9dd21bbad0de913e9b12ab5244f2f7eb
--- /dev/null
+++ b/heatmaps/Mixtral-8x7B-Instruct-v0.1_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd1c72aafdf96102115d66d1ef4e8941cd3e75007d4769f253913d92fd3ee11
+size 1322927
diff --git a/heatmaps/Mixtral-8x7B-Instruct-v0.1_Textonly.jpg b/heatmaps/Mixtral-8x7B-Instruct-v0.1_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..880b3b8925c7423febf6257fed60f91a6ab8d2e4
--- /dev/null
+++ b/heatmaps/Mixtral-8x7B-Instruct-v0.1_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7433170eae759affb90bd714dcc655831503d483c82f9878bd3d5607a4448476
+size 1322161
diff --git a/heatmaps/Qwen1.5-72B-Chat_CoT.jpg b/heatmaps/Qwen1.5-72B-Chat_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..4fab291ecebc019ad6e4dbb51d98afdffe765371
--- /dev/null
+++ b/heatmaps/Qwen1.5-72B-Chat_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b607383ae11aa64e0058dbfbc294c1366054ac3bd2910d7803de604ee75dcf5
+size 1310959
diff --git a/heatmaps/Qwen1.5-72B-Chat_Textonly.jpg b/heatmaps/Qwen1.5-72B-Chat_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..3498b8bc415774f9dfd1a72ec0a21ce0f90258cb
--- /dev/null
+++ b/heatmaps/Qwen1.5-72B-Chat_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec21974c9b3987b565a2e152af9c2b33b1b15d054389a3ab8ca4635d67830c8c
+size 1312541
diff --git a/heatmaps/Yi-34B-Chat_CoT.jpg b/heatmaps/Yi-34B-Chat_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..bf72a49c4d2bee59b896f21028b601ca978b3119
--- /dev/null
+++ b/heatmaps/Yi-34B-Chat_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e486fb5d66e68c02cfefe02527ce9c9768742c3aefa98f218a4f45fa5f390bd2
+size 1326266
diff --git a/heatmaps/Yi-34B-Chat_Textonly.jpg b/heatmaps/Yi-34B-Chat_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..971273846ebfbf849a8f77feaeb6a0972e61fa33
--- /dev/null
+++ b/heatmaps/Yi-34B-Chat_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277071c8daf563feff3de2f0ce819bc56a3d2d2ba87d7862ff7684f1abd02bdb
+size 1323087
diff --git a/heatmaps/claude-3-haiku-20240307_1shot.jpg b/heatmaps/claude-3-haiku-20240307_1shot.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..fda8b83e4b6e94002dbe2a6ab86bbb57ea07ceb0
--- /dev/null
+++ b/heatmaps/claude-3-haiku-20240307_1shot.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1d76eeccd60fab64bdba46234b5445bc8e827765c78f86cf1f7139cf5ac392
+size 1298150
diff --git a/heatmaps/claude-3-haiku-20240307_CoT.jpg b/heatmaps/claude-3-haiku-20240307_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..38e3ef40873193c58adb977e625e8306c8529c87
--- /dev/null
+++ b/heatmaps/claude-3-haiku-20240307_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30a5e503b394d209b6b626efec0f8240061b2aa2f84043d2172179127cb1021
+size 1303986
diff --git a/heatmaps/claude-3-haiku-20240307_Textonly.jpg b/heatmaps/claude-3-haiku-20240307_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7d207abdd1abd5bbbd4848af486fa6607673a87a
--- /dev/null
+++ b/heatmaps/claude-3-haiku-20240307_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ceaabc9a0e37b39f419dbdc06d9db85154084ed752c857e4d6b66daa829741
+size 1303392
diff --git a/heatmaps/claude-3-haiku-20240307_vision-CoT.jpg b/heatmaps/claude-3-haiku-20240307_vision-CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..f9c9d3074c8e356df604e1d27bce58e6df3c0f6f
--- /dev/null
+++ b/heatmaps/claude-3-haiku-20240307_vision-CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03395379bdfaf4f2a199a0b3b13b297d78a2e1a70dd0c466c155b2d1d76d5d0
+size 1323987
diff --git a/heatmaps/claude-3-haiku-20240307_vision.jpg b/heatmaps/claude-3-haiku-20240307_vision.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..f649f16f13d490f24ba9a5d918d5ad02b8a2a5b8
--- /dev/null
+++ b/heatmaps/claude-3-haiku-20240307_vision.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1237260665f554651e781141211f0a713167f68e61a6683ad652cc1f00020c
+size 1324943
diff --git a/heatmaps/claude-3-opus-20240229_CoT.jpg b/heatmaps/claude-3-opus-20240229_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a411dbd47760df06cbeafd771e1a38caff85a873
--- /dev/null
+++ b/heatmaps/claude-3-opus-20240229_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382fa0ff6881fcc78056d4025343f521d5e047c370e6b4d20cbbb6ef140a1e46
+size 1212580
diff --git a/heatmaps/claude-3-opus-20240229_Textonly.jpg b/heatmaps/claude-3-opus-20240229_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..69a58927191c0532cde7aa3d4f28921a3fced8cc
--- /dev/null
+++ b/heatmaps/claude-3-opus-20240229_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576298ca335a6da82c6c7c4144639a4a92c2b902674430fab1eb38d91d93e5bb
+size 1211439
diff --git a/heatmaps/claude-3-opus-20240229_vision-CoT.jpg b/heatmaps/claude-3-opus-20240229_vision-CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..9cfca3a1ecc563234b27a91e3740e3b0037acb55
--- /dev/null
+++ b/heatmaps/claude-3-opus-20240229_vision-CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6ac07ac9337a62d6b0152e6b3582405f5ded6197ec31e0370952f2df38c3be
+size 1334518
diff --git a/heatmaps/claude-3-opus-20240229_vision.jpg b/heatmaps/claude-3-opus-20240229_vision.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7fc39cf8231dfe510b8c859001338aeb04a7233c
--- /dev/null
+++ b/heatmaps/claude-3-opus-20240229_vision.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5056abaef945199d6ef4e3833ae20ca763c80aff44ca59d991567637dee4d237
+size 1334486
diff --git a/heatmaps/claude-3-sonnet-20240229_CoT.jpg b/heatmaps/claude-3-sonnet-20240229_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..cfcec38cbfb44c696a3adca6f13275f949c3e454
--- /dev/null
+++ b/heatmaps/claude-3-sonnet-20240229_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f3fcc436adf32351392db6fe0b36969554ecfef9f5a6be87d6cb73b59d3840
+size 1333230
diff --git a/heatmaps/claude-3-sonnet-20240229_Textonly.jpg b/heatmaps/claude-3-sonnet-20240229_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..95fe7bdca0a4dd712b65bf506ff79ba9a0a932b3
--- /dev/null
+++ b/heatmaps/claude-3-sonnet-20240229_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3d02435e530cf058e48fd6262d23131656aec109f09c64349fac30338a4988
+size 1288600
diff --git a/heatmaps/claude-3-sonnet-20240229_vision-CoT.jpg b/heatmaps/claude-3-sonnet-20240229_vision-CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..f5e7887e4e52829671905c9e7d05e83e2d312a68
--- /dev/null
+++ b/heatmaps/claude-3-sonnet-20240229_vision-CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63f154b6c312cd298c32cf805a00118922dd8fd7da1169a8b64d415740a1ebc
+size 1328463
diff --git a/heatmaps/claude-3-sonnet-20240229_vision.jpg b/heatmaps/claude-3-sonnet-20240229_vision.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..11b199b920d3f006cc3075d4dedde5bf643ce0b4
--- /dev/null
+++ b/heatmaps/claude-3-sonnet-20240229_vision.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea55e964a1547d4462364c8f41ecbaf870af6cb151589bc45af03bbcc171afad
+size 1280445
diff --git a/heatmaps/dbrx-instruct_CoT.jpg b/heatmaps/dbrx-instruct_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..c44d58f42f7b597f267850a66acd2d99ef7e5eab
--- /dev/null
+++ b/heatmaps/dbrx-instruct_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8720a093a238c8312629c46c0b54e62aa1a95059dce9ec5b269508450acd21a6
+size 1324782
diff --git a/heatmaps/dbrx-instruct_Textonly.jpg b/heatmaps/dbrx-instruct_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a8ee55cb35375eed7f7821a8b097301175307c37
--- /dev/null
+++ b/heatmaps/dbrx-instruct_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208c1caeaa0c862c0cadb4a6f017906f1e1925383b09d6b9929732a71618984e
+size 1321204
diff --git a/heatmaps/deepseek-llm-67b-chat_CoT.jpg b/heatmaps/deepseek-llm-67b-chat_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..cad3aa7d202936aadc12d684de0352d2d58e607b
--- /dev/null
+++ b/heatmaps/deepseek-llm-67b-chat_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0299b8c3d112641c428a5c77d368b92a8560908221b214a63b91a8f2ce97a070
+size 1319713
diff --git a/heatmaps/deepseek-llm-67b-chat_Textonly.jpg b/heatmaps/deepseek-llm-67b-chat_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..70485757df137396f4df50280db54e591ef8c008
--- /dev/null
+++ b/heatmaps/deepseek-llm-67b-chat_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59e661ad07580f7bd280be46e26caeec50fa082920bd4e0e7ad5be1653fb116
+size 1325710
diff --git a/heatmaps/gemini-pro_CoT.jpg b/heatmaps/gemini-pro_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..4fad50b4b142afa366fb9675448be08a1d1fe3ad
--- /dev/null
+++ b/heatmaps/gemini-pro_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73ac717609221026e584cbf2ba76538d6091459eccb63763142faa8cd233a82
+size 1322532
diff --git a/heatmaps/gemini-pro_vision-CoT.jpg b/heatmaps/gemini-pro_vision-CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..397db7b8c1e30301d62da537c35e25b123a0ea78
--- /dev/null
+++ b/heatmaps/gemini-pro_vision-CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116b2a07fb740560e59471347f4c6da6fbb251ef0a6cda7f4c3cd9cf8ef2beac
+size 1325582
diff --git a/heatmaps/gemini-pro_vision.jpg b/heatmaps/gemini-pro_vision.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..4a6576b8f66f2de2a334d22f8b76369896afca6f
--- /dev/null
+++ b/heatmaps/gemini-pro_vision.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36cc139756d58b144d03cffdd23df7a07a71f1a3b77d8544b35d24afbece3a10
+size 1328654
diff --git a/heatmaps/gemma-7b-it_CoT.jpg b/heatmaps/gemma-7b-it_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7db6b466274b631ad66115e2d9eba25431232432
--- /dev/null
+++ b/heatmaps/gemma-7b-it_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7abc637ee1f0206737eeecef445c785c8de7d7a8830e1a4dd3934453c497dc1
+size 1337084
diff --git a/heatmaps/gemma-7b-it_Textonly.jpg b/heatmaps/gemma-7b-it_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..e51cf97c98a4ac2c347bc9707a18e27140412119
--- /dev/null
+++ b/heatmaps/gemma-7b-it_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e436e4d353b0de47a639aaf10fe1aa61ea59e9020b83924a6f38f023177c1631
+size 1323814
diff --git a/heatmaps/gpt-3.5-0613_CoT.jpg b/heatmaps/gpt-3.5-0613_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..50af6c75507cee4005726e5eacac7809c279aafc
--- /dev/null
+++ b/heatmaps/gpt-3.5-0613_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36f991250d11adf955df905756e4abb8313fb2f46a06bb6e4fb1c1f117dd332
+size 1318275
diff --git a/heatmaps/gpt-3.5-0613_Textonly.jpg b/heatmaps/gpt-3.5-0613_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..d1c1611e809ca2f99310544e973e10738703dba4
--- /dev/null
+++ b/heatmaps/gpt-3.5-0613_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cc450248c9ce976f6eb76d148c75ff1087499a585c2dd12fd8c3c27e1f1ce2
+size 1321315
diff --git a/heatmaps/gpt-3.5-turbo-0125_1shot.jpg b/heatmaps/gpt-3.5-turbo-0125_1shot.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..21eb4858c370c73097a5a05b0c1cf8096c49265f
--- /dev/null
+++ b/heatmaps/gpt-3.5-turbo-0125_1shot.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45770b4c8e836e17cccb2ad73ed7894802f070fbfb760c166881a9ada6eccaa5
+size 1316586
diff --git a/heatmaps/gpt-3.5-turbo-0125_CoT.jpg b/heatmaps/gpt-3.5-turbo-0125_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..f147fd01316f585e90746b7b9764f2253f5726e4
--- /dev/null
+++ b/heatmaps/gpt-3.5-turbo-0125_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ebed5226148f5222839dd16aec869786bf608e66320a77eadaaa2633808189c
+size 1320380
diff --git a/heatmaps/gpt-3.5-turbo-0125_Textonly.jpg b/heatmaps/gpt-3.5-turbo-0125_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..9a392f1bd8ac47072debc29d4d81b9e6f3af0824
--- /dev/null
+++ b/heatmaps/gpt-3.5-turbo-0125_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f8baca85b9833cad9236fc7b94e0f645f5d9979d200eb49b086b2219ac7b7e
+size 1322724
diff --git a/heatmaps/gpt-4-0125-preview_CoT.jpg b/heatmaps/gpt-4-0125-preview_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..13f44feae78a4bc159822acf85cbb162460fd813
--- /dev/null
+++ b/heatmaps/gpt-4-0125-preview_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4af344d9bdf4aac858531ac565bc09235774629e0f4a6485f13b01bbb98835
+size 1232100
diff --git a/heatmaps/gpt-4-0125-preview_Textonly.jpg b/heatmaps/gpt-4-0125-preview_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..6a47ea8c4ac8412385139f702e4ef79007f03d74
--- /dev/null
+++ b/heatmaps/gpt-4-0125-preview_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d339d6e1527fa18f390ca34ab0ba833a9a187109396c638f2e4ec1c16be11f3a
+size 1237947
diff --git a/heatmaps/gpt-4-1106_CoT.jpg b/heatmaps/gpt-4-1106_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..cc77cf3fcc0d47524f9a5323a2e2b2cc726660a0
--- /dev/null
+++ b/heatmaps/gpt-4-1106_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce05c6404989f6ec8653bfd7fe9839c536cdce24ef75f6cd1fdb4800eba766c3
+size 1233202
diff --git a/heatmaps/gpt-4-1106_Textonly.jpg b/heatmaps/gpt-4-1106_Textonly.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..db435d6eb04a68cd455435e1e59ca4a538b5b34c
--- /dev/null
+++ b/heatmaps/gpt-4-1106_Textonly.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf8c95dc35b8277b7a2b5e9a08e366f0152af08ee78c398f12bc083a29adb94
+size 1235790
diff --git a/heatmaps/gpt-4-turbo-2024-04-09_CoT.jpg b/heatmaps/gpt-4-turbo-2024-04-09_CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..c43875d4dc84020a90268a02c911a816a909dba1
--- /dev/null
+++ b/heatmaps/gpt-4-turbo-2024-04-09_CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3e95c1c0459f483504cf4c34034ddb3a68bac4cbab158627af90034686b6d3
+size 1224951
diff --git a/results/gpt-4-turbo-2024-04-09.jpg b/heatmaps/gpt-4-turbo-2024-04-09_Textonly.jpg
similarity index 100%
rename from results/gpt-4-turbo-2024-04-09.jpg
rename to heatmaps/gpt-4-turbo-2024-04-09_Textonly.jpg
diff --git a/heatmaps/gpt-4-vision-preview_vision-CoT.jpg b/heatmaps/gpt-4-vision-preview_vision-CoT.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..d61b96c4f4c2411ec1cc976b647477bd24fa4859
--- /dev/null
+++ b/heatmaps/gpt-4-vision-preview_vision-CoT.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910c2d4820c49249d143e390f500aa149f68ba00a56c3fcb0c61b2485e93d3ab
+size 1319084
diff --git a/heatmaps/gpt-4-vision-preview_vision.jpg b/heatmaps/gpt-4-vision-preview_vision.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7f22eee19e8c3c0088dae371baea2ce5b9964659
--- /dev/null
+++ b/heatmaps/gpt-4-vision-preview_vision.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cd741abe572de14c59286eaa8ae830bc20ca142035a4adfc39fc9641354379
+size 1321753
diff --git a/results/CodeLlama-70b-Instruct-hf.jpg b/results/CodeLlama-70b-Instruct-hf.jpg
deleted file mode 100644
index 00f7e00e1535297ee0bacc7543cb125ff27ce556..0000000000000000000000000000000000000000
--- a/results/CodeLlama-70b-Instruct-hf.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:775abffec22b340287e4135903e47fa07097fd38e26a9d2d11dc9db852bc1edd
-size 1322923
diff --git a/results/CodeLlama-70b-Instruct-hf.pkl b/results/CodeLlama-70b-Instruct-hf.pkl
deleted file mode 100644
index 97f70aa9681a378e58e44e780a5b58b8a5445157..0000000000000000000000000000000000000000
--- a/results/CodeLlama-70b-Instruct-hf.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5f2b9c13f7266d94ffe12c040118a5a0b208e85cbf4a5aab5b12eee4bd0c5384
-size 14963090
diff --git a/results/CodeLlama-70b-Instruct-hf.png b/results/CodeLlama-70b-Instruct-hf.png
deleted file mode 100644
index 913d89408049f90c7700ec267d45ddd9adbcfd9d..0000000000000000000000000000000000000000
--- a/results/CodeLlama-70b-Instruct-hf.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:edd3d40b297c5a8b3292c03c974c2c5705348dd29a763db6ef8651bcdcd5e9c8
-size 1014517
diff --git a/results/GPT-4-0125-preview.jpg b/results/GPT-4-0125-preview.jpg
deleted file mode 100644
index 1b7b0319680c5d2cfcf343308b13801a3858f816..0000000000000000000000000000000000000000
--- a/results/GPT-4-0125-preview.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9760db664e239b5e05ad002259bb0b2e76c0a9a7c6ad03cdb6a09a2e8c265077
-size 1238797
diff --git a/results/GPT-4-0125-preview.pkl b/results/GPT-4-0125-preview.pkl
deleted file mode 100644
index c39dbaa38e00d1a1797ced345fcb1759ba90b574..0000000000000000000000000000000000000000
--- a/results/GPT-4-0125-preview.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:46a3b7e6c49fcfb82921451a9f3fdb2c3630eee5b24fcc4ae6ca48c1af777e63
-size 15972703
diff --git a/results/GPT-4-0125-preview.png b/results/GPT-4-0125-preview.png
deleted file mode 100644
index 4d2d5f1bae98843abdd78257d534b4ef8fb80636..0000000000000000000000000000000000000000
--- a/results/GPT-4-0125-preview.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:53dd196468fa09306ebd284a7a46fa7c363f4b6e5c768184d049548f2eeca205
-size 1007830
diff --git a/results/Llama-2-70b-chat-hf.jpg b/results/Llama-2-70b-chat-hf.jpg
deleted file mode 100644
index 0e8e84953e40368d90c67ae0c71b4211744e7039..0000000000000000000000000000000000000000
--- a/results/Llama-2-70b-chat-hf.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4f7e46612db42e32889834bc632ca34fab32216cb39f413d3f058c70681c32e9
-size 1326313
diff --git a/results/Llama-2-70b-chat-hf.pkl b/results/Llama-2-70b-chat-hf.pkl
deleted file mode 100644
index d054837fbce4aa6b6a9aead032ea87125acd15b5..0000000000000000000000000000000000000000
--- a/results/Llama-2-70b-chat-hf.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c35b23dcd598daf63fb74f7d21e06a217f4b93cc152666ac93c000a2a9b94808
-size 18381134
diff --git a/results/Llama-2-70b-chat-hf.png b/results/Llama-2-70b-chat-hf.png
deleted file mode 100644
index e31e17ac143f34556156300f14a727243f88ceec..0000000000000000000000000000000000000000
--- a/results/Llama-2-70b-chat-hf.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:47c89899f3372c274cf073fbf451918cf17ff11347fb70b05dca4e2890b35649
-size 1012937
diff --git a/results/Llama-3-70b-chat-hf.jpg b/results/Llama-3-70b-chat-hf.jpg
deleted file mode 100644
index 620ad4612171d18e63cc76535302dfff54381ebb..0000000000000000000000000000000000000000
--- a/results/Llama-3-70b-chat-hf.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cae0df063a8185360cc474e03f1456c09d5f6e111f8d654ec06f857e88e658dc
-size 1288099
diff --git a/results/Llama-3-70b-chat-hf.pkl b/results/Llama-3-70b-chat-hf.pkl
deleted file mode 100644
index 8e9356b2a6c7d2efda96608ca9049b22497399fe..0000000000000000000000000000000000000000
--- a/results/Llama-3-70b-chat-hf.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ab6231fa25049b3451ed54256f9c02c5b4235a04595a50aeefe82b33596fd76a
-size 15966316
diff --git a/results/Llama-3-70b-chat-hf.png b/results/Llama-3-70b-chat-hf.png
deleted file mode 100644
index ba45ab6f528a8e3e96f36151a037968cba0393d0..0000000000000000000000000000000000000000
--- a/results/Llama-3-70b-chat-hf.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:35b702600899a9f010b2c9ff8fb1172d6dcda12d787943df61ede830cd21693f
-size 1007396
diff --git a/results/Mistral-7B-Instruct-v0.2.jpg b/results/Mistral-7B-Instruct-v0.2.jpg
deleted file mode 100644
index f3c39b0b2812afac77e329f05a0a14f93a901c43..0000000000000000000000000000000000000000
--- a/results/Mistral-7B-Instruct-v0.2.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:365677f0f3296b85dd3907cccfbd647ac752fc85c7ad24cf780fe7d95f579659
-size 1324731
diff --git a/results/Mistral-7B-Instruct-v0.2.pkl b/results/Mistral-7B-Instruct-v0.2.pkl
deleted file mode 100644
index 26a6b915f60d97b28fb16b0689e91e10c89d428b..0000000000000000000000000000000000000000
--- a/results/Mistral-7B-Instruct-v0.2.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ee64e642a1e03676eb214dd13e455f77a9c2ab2a699935a3f66aff5e6c2110e
-size 25112380
diff --git a/results/Mistral-7B-Instruct-v0.2.png b/results/Mistral-7B-Instruct-v0.2.png
deleted file mode 100644
index f634e9814c35087f44c0499395d70fcbb9e6eb9f..0000000000000000000000000000000000000000
--- a/results/Mistral-7B-Instruct-v0.2.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1eea8bf43a8c2a8ef01c4dcfbb22c744902b778adcb70d3dd47bb132410a57a6
-size 1013351
diff --git a/results/Mixtral-8x7B-Instruct-v0.1.jpg b/results/Mixtral-8x7B-Instruct-v0.1.jpg
deleted file mode 100644
index ce247014f4c501ae7e7d20227b0bc2f0d2d2420b..0000000000000000000000000000000000000000
--- a/results/Mixtral-8x7B-Instruct-v0.1.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8bd1ca2488a739fcdf331326c29a1bed80bb887ca0a4ae304569503712de9310
-size 1322552
diff --git a/results/Mixtral-8x7B-Instruct-v0.1.pkl b/results/Mixtral-8x7B-Instruct-v0.1.pkl
deleted file mode 100644
index caa22e28301b059a7448b497d1c8a981f93c19d8..0000000000000000000000000000000000000000
--- a/results/Mixtral-8x7B-Instruct-v0.1.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a91a52a2452f33a7e880f2c93bb3384eef3c09ef245ee3c48280f0a75a18c3bd
-size 15622486
diff --git a/results/Mixtral-8x7B-Instruct-v0.1.png b/results/Mixtral-8x7B-Instruct-v0.1.png
deleted file mode 100644
index 32fe06f83799e247597c38db572b972132bc311d..0000000000000000000000000000000000000000
--- a/results/Mixtral-8x7B-Instruct-v0.1.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76018c7481c7f08d5a622f761620fcdfb60ee6851083a2feffcdcc6d6e231fd4
-size 1015123
diff --git a/results/Qwen1.5-72B-Chat.jpg b/results/Qwen1.5-72B-Chat.jpg
deleted file mode 100644
index e30a59df05f7e0519d51b38ccb03581ae22ed7b9..0000000000000000000000000000000000000000
--- a/results/Qwen1.5-72B-Chat.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3fa1bf7ad4a076a198c9725d65d51814b64e9e2233d7fa21581e6a92913fe1d0
-size 1312846
diff --git a/results/Qwen1.5-72B-Chat.pkl b/results/Qwen1.5-72B-Chat.pkl
deleted file mode 100644
index 26d6806e09a682e65c43f547e9c276c20e4fd0c5..0000000000000000000000000000000000000000
--- a/results/Qwen1.5-72B-Chat.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe09314e36e70f99fc301f0c21b3de4f67257a535be70dc1653a95a5a8da5003
-size 12117010
diff --git a/results/Qwen1.5-72B-Chat.png b/results/Qwen1.5-72B-Chat.png
deleted file mode 100644
index 578292b39fe318421f7faf619281e980b5e4566a..0000000000000000000000000000000000000000
--- a/results/Qwen1.5-72B-Chat.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:af79b199f0084ffcd2edf6da4f3a0718c34da4832911fb59aff8887f9bcb7e3a
-size 1014450
diff --git a/results/Yi-34B-Chat.jpg b/results/Yi-34B-Chat.jpg
deleted file mode 100644
index 3e297f64e5e26fb1a51cb05aa7b230f6efda51d3..0000000000000000000000000000000000000000
--- a/results/Yi-34B-Chat.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2aac2319f74bb4fceeed1a80134e9b2ad7e0ce0cb24d391e63bd822501d202ad
-size 1323170
diff --git a/results/Yi-34B-Chat.pkl b/results/Yi-34B-Chat.pkl
deleted file mode 100644
index 5b8436218f4a10789f4eba9339956ece4de344a5..0000000000000000000000000000000000000000
--- a/results/Yi-34B-Chat.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f8e2d70bb8c16f9f28445729bdb58111e4303f103e829e1d5c3f4b01dc701866
-size 18357438
diff --git a/results/Yi-34B-Chat.png b/results/Yi-34B-Chat.png
deleted file mode 100644
index a15169237a8bcce2a3f654dad463ca1d2f3e068b..0000000000000000000000000000000000000000
--- a/results/Yi-34B-Chat.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06c66a8890d9d44b170c282bf20dbb349b06f84075e55a9baec46a26aa7fb9a3
-size 1013684
diff --git a/results/claude-3-haiku-20240307.jpg b/results/claude-3-haiku-20240307.jpg
deleted file mode 100644
index dee1cb635583e4d463a22be8e1c75ff51be853b4..0000000000000000000000000000000000000000
--- a/results/claude-3-haiku-20240307.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b7ab74bfdd0edc6b004ecf50c2cd6601d8c3ce3dee13d43b53a9e44921fd0cf
-size 1303664
diff --git a/results/claude-3-haiku-20240307.pkl b/results/claude-3-haiku-20240307.pkl
deleted file mode 100644
index 7f69728cf6a1ccf7cd6cd1d4526c10360ab75ec7..0000000000000000000000000000000000000000
--- a/results/claude-3-haiku-20240307.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e19e05ac9badf9f39455c366b8bf05ea40c0aae8cd66fd53016c50d085cea647
-size 17770468
diff --git a/results/claude-3-haiku-20240307.png b/results/claude-3-haiku-20240307.png
deleted file mode 100644
index e9dc0a9499e167d5f3b04ae910132c9e9ba6971a..0000000000000000000000000000000000000000
--- a/results/claude-3-haiku-20240307.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aff9411b96a6aaae1d50b352c2e778ff32f26cbbb2bfc5d5ddc572aaa21d986e
-size 1012936
diff --git a/results/claude-3-opus-20240229.jpg b/results/claude-3-opus-20240229.jpg
deleted file mode 100644
index 7ad221a0aeb57b3992087d36a60eca381d7c76a9..0000000000000000000000000000000000000000
--- a/results/claude-3-opus-20240229.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1cb2e58994183de9eebda61c1741522466657e5916c543ea8a646afb9133a2c9
-size 1212166
diff --git a/results/claude-3-opus-20240229.pkl b/results/claude-3-opus-20240229.pkl
deleted file mode 100644
index fe3fc1b7fc65fea8cd5c450638f62c536677b62e..0000000000000000000000000000000000000000
--- a/results/claude-3-opus-20240229.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b47707ac006a490b607c1280c1013cb1de466434e5c518fff427a229bab46aa
-size 18241965
diff --git a/results/claude-3-opus-20240229.png b/results/claude-3-opus-20240229.png
deleted file mode 100644
index 580184a49c23e662e81b235ed8266666e191c752..0000000000000000000000000000000000000000
--- a/results/claude-3-opus-20240229.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:13ce4f0ea785209f7c193702c9e41988f6f8e74824cb05a53503264aee626b89
-size 1007456
diff --git a/results/claude-3-sonnet-20240229.jpg b/results/claude-3-sonnet-20240229.jpg
deleted file mode 100644
index ade4e00f07072aa8472ac14ccf0d083382698565..0000000000000000000000000000000000000000
--- a/results/claude-3-sonnet-20240229.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:57c1109826861ee9b4e16ff1abd28cf58afb2e49495305257a3c466c6db21d5c
-size 1290164
diff --git a/results/claude-3-sonnet-20240229.pkl b/results/claude-3-sonnet-20240229.pkl
deleted file mode 100644
index 7ec8cd8e0a3c58841484160e0a47f1339f1201a9..0000000000000000000000000000000000000000
--- a/results/claude-3-sonnet-20240229.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b80e820a34180cdb4e2393c170b08aa7046312f01a5bfbbbf7024ef7e1c94e22
-size 20950616
diff --git a/results/claude-3-sonnet-20240229.png b/results/claude-3-sonnet-20240229.png
deleted file mode 100644
index 629481ec1c1f3b765b6ebb949f2f787369d356de..0000000000000000000000000000000000000000
--- a/results/claude-3-sonnet-20240229.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:07eb457f7638ced88b2fd2f8880b821360963b72d2ecdc408d84bf059f32ab75
-size 1007664
diff --git a/results/dbrx-instruct.jpg b/results/dbrx-instruct.jpg
deleted file mode 100644
index 9a50e7b6d4fe985dbebbe369c30aca7df3890481..0000000000000000000000000000000000000000
--- a/results/dbrx-instruct.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c9eaa342dbdb13cb51a3f2584cc56720a37fc0a785e1e939a910ab3bf5384983
-size 1321040
diff --git a/results/dbrx-instruct.pkl b/results/dbrx-instruct.pkl
deleted file mode 100644
index 25e069ca4fc5d230ee7259b615d0813dbdf848fe..0000000000000000000000000000000000000000
--- a/results/dbrx-instruct.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c33881cb23d9859f5ab0b3e8c7df9218ae2046dce2f5ac20b418ce6ced19989
-size 15797034
diff --git a/results/dbrx-instruct.png b/results/dbrx-instruct.png
deleted file mode 100644
index 2a2fdbe990f39ff1121b4b5314ecc4a19fa19052..0000000000000000000000000000000000000000
--- a/results/dbrx-instruct.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6394ede90549565b9df5256fc8b2779d6c05484d41b2b21ac725051b1368c782
-size 1016807
diff --git a/results/deepseek-llm-67b-chat.jpg b/results/deepseek-llm-67b-chat.jpg
deleted file mode 100644
index ed5e43692fac7946fad783c8ba853d0e6ab9be4e..0000000000000000000000000000000000000000
--- a/results/deepseek-llm-67b-chat.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ffe70df8cd91f20066816e092131ea5896121b689f02292b1ddbe21661963077
-size 1325680
diff --git a/results/deepseek-llm-67b-chat.pkl b/results/deepseek-llm-67b-chat.pkl
deleted file mode 100644
index ac219e477c1e646237803cccd9ba1deb18a8cadd..0000000000000000000000000000000000000000
--- a/results/deepseek-llm-67b-chat.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7f4f015cc17f9b5ccd1c2367fac5b9fabc7a7917283c17ad875e87dea7e07f53
-size 12932443
diff --git a/results/deepseek-llm-67b-chat.png b/results/deepseek-llm-67b-chat.png
deleted file mode 100644
index 4a2223bf39f734024c840b7c6c6b509b7fad0150..0000000000000000000000000000000000000000
--- a/results/deepseek-llm-67b-chat.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:84fdb1e33c83ed49a6187abd140969372c8eda7f5d3f5cbb57d486ce7c530d75
-size 1013925
diff --git a/results/gemma-7b-it.jpg b/results/gemma-7b-it.jpg
deleted file mode 100644
index cb20abd3754304349715f22dd8e39171031d123c..0000000000000000000000000000000000000000
--- a/results/gemma-7b-it.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b20f35a5909d458db4a08f13c6524977a5f0bf51c25c811adbd7dbbdd4c4bae3
-size 1324126
diff --git a/results/gemma-7b-it.pkl b/results/gemma-7b-it.pkl
deleted file mode 100644
index 31d90c1b5bea0a45b3846fbfa3a9a7b019da4405..0000000000000000000000000000000000000000
--- a/results/gemma-7b-it.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:213281bf9dca05136d64b61e2d8920e947bb6c908c8ea989b006eb73ad0d9b92
-size 11293622
diff --git a/results/gemma-7b-it.png b/results/gemma-7b-it.png
deleted file mode 100644
index cb1e7b512c05d13448830fa756adfdf41ce1dcc6..0000000000000000000000000000000000000000
--- a/results/gemma-7b-it.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:95c811dc77e6afe9079e577060f3710668326c021d0775e44da11b48b1766488
-size 1010924
diff --git a/results/gpt-3.5-0613.jpg b/results/gpt-3.5-0613.jpg
deleted file mode 100644
index cb3e9360847c539173fa820750b73e0fca3e0622..0000000000000000000000000000000000000000
--- a/results/gpt-3.5-0613.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2cda6a309b0e8361a8741e233c8dd747dec9d50f66cc56b99f6f3b22335d9824
-size 1321225
diff --git a/results/gpt-3.5-0613.pkl b/results/gpt-3.5-0613.pkl
deleted file mode 100644
index b93e0f43172ebf4bce23edd193679006176c7117..0000000000000000000000000000000000000000
--- a/results/gpt-3.5-0613.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8e10584a651923db281667540e54cb56d86a97a74676a95f4a97e6575800574e
-size 8655742
diff --git a/results/gpt-3.5-0613.png b/results/gpt-3.5-0613.png
deleted file mode 100644
index 762edac14ebb6b581e3eeacaad5a38b4a9e9036b..0000000000000000000000000000000000000000
--- a/results/gpt-3.5-0613.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:93badcf64e215daf80be4d75ebbd32d8ae8afc0541a9a480558fa30580165f4c
-size 1012969
diff --git a/results/gpt-3.5-turbo-0125.jpg b/results/gpt-3.5-turbo-0125.jpg
deleted file mode 100644
index 2be8d64c7737ccda4e65df0027a5ebf0a853db5c..0000000000000000000000000000000000000000
--- a/results/gpt-3.5-turbo-0125.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0b8b383520abab7a0f1f8c2194f7597a879d2e5462d602f54f598518d6038f01
-size 1322712
diff --git a/results/gpt-3.5-turbo-0125.pkl b/results/gpt-3.5-turbo-0125.pkl
deleted file mode 100644
index 5a2756f3b97fadc014f8e1b58b2f048f17901af3..0000000000000000000000000000000000000000
--- a/results/gpt-3.5-turbo-0125.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6248651aa308b7e1a4c903b0e0054ea8e1d3c643c5d1335d2d79c13a9cc68ddc
-size 8052825
diff --git a/results/gpt-3.5-turbo-0125.png b/results/gpt-3.5-turbo-0125.png
deleted file mode 100644
index fbe3937c339ccfa7ae43e96a74a0951eaf302f6a..0000000000000000000000000000000000000000
--- a/results/gpt-3.5-turbo-0125.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19906ee7210d494f2099dc7228b7bdf6963c399507fec85658f496c79f50cfd3
-size 1014303
diff --git a/results/gpt-4-1106.jpg b/results/gpt-4-1106.jpg
deleted file mode 100644
index 713b04381b3362205b7b05271d9910ab85f60be7..0000000000000000000000000000000000000000
--- a/results/gpt-4-1106.jpg
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:00b3589bff4da14aac5503f0b83331d3ea1b515ea900e57d40b555693b9ec1e4
-size 1238681
diff --git a/results/gpt-4-1106.pkl b/results/gpt-4-1106.pkl
deleted file mode 100644
index 100d225e3b4881c5ffd825a889ce4aafafaeda1f..0000000000000000000000000000000000000000
--- a/results/gpt-4-1106.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:66aa682ff3b8862a20e86a1383733f231f97817735b5360c664ae96b6010f056
-size 16856594
diff --git a/results/gpt-4-1106.png b/results/gpt-4-1106.png
deleted file mode 100644
index f5600321f2a6cecfda372303651efd7ad03ea9cc..0000000000000000000000000000000000000000
--- a/results/gpt-4-1106.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ab1b0db31db1b9945e9aa0ae68cd95c0a572570f1814efc504d63493894f292d
-size 1007682
diff --git a/results/gpt-4-turbo-2024-04-09.pkl b/results/gpt-4-turbo-2024-04-09.pkl
deleted file mode 100644
index b7c8baaf351257c84f3129495eacc83e7e5b9437..0000000000000000000000000000000000000000
--- a/results/gpt-4-turbo-2024-04-09.pkl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe679c7d7fd96a8f0e62c6993795d8b5039ab70523c0f21ba851c3e95c33b9b7
-size 16528892
diff --git a/results/gpt-4-turbo-2024-04-09.png b/results/gpt-4-turbo-2024-04-09.png
deleted file mode 100644
index 7ffe3c400f708cab5a7f9ea54451a6e363577424..0000000000000000000000000000000000000000
--- a/results/gpt-4-turbo-2024-04-09.png
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c212b5d2f5c413940ba464adacef8fcec7d83f1abdacc9548b520879ef4bdf1b
-size 1007985