Add gpt4 and gpt3 reference json files

data/mt_bench_radar.ipynb

@@ -0,0 +1,714 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Vp5YVvaTpIiX",
+        "outputId": "3c5b2a63-1fb4-430d-a986-4092ee8d4891"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "--2023-11-28 19:52:23--  https://huggingface.co/spaces/lmsys/mt-bench/resolve/main/data/mt_bench/model_judgment/gpt-4_single.jsonl\n",
+            "Resolving huggingface.co (huggingface.co)... 18.164.174.55, 18.164.174.23, 18.164.174.118, ...\n",
+            "Connecting to huggingface.co (huggingface.co)|18.164.174.55|:443... connected.\n",
+            "HTTP request sent, awaiting response... 302 Found\n",
+            "Location: https://cdn-lfs.huggingface.co/repos/12/2b/122bd8e9eccbb3acc98acf73e0ecef3c96f24dcdb5f6639074ed304eb19f9cd4/76c55033c6b2b1cc3f62513458f84748a23352495fd42b1062a7401de5ff9bd9?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27gpt-4_single.jsonl%3B+filename%3D%22gpt-4_single.jsonl%22%3B&Expires=1701460343&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcwMTQ2MDM0M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8xMi8yYi8xMjJiZDhlOWVjY2JiM2FjYzk4YWNmNzNlMGVjZWYzYzk2ZjI0ZGNkYjVmNjYzOTA3NGVkMzA0ZWIxOWY5Y2Q0Lzc2YzU1MDMzYzZiMmIxY2MzZjYyNTEzNDU4Zjg0NzQ4YTIzMzUyNDk1ZmQ0MmIxMDYyYTc0MDFkZTVmZjliZDk%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=hwTqBVlLz755xHaQaN6cSDP2FxoPBAXFcOE2uvFAYzg0Y90kGkY3A74Fj2wAkToA-dN1WJeMc%7Ef2XarD%7EbAw%7E4v2JCw9kphUxL-pcRF1uNBI2pzS-3Joff-m%7Ee3GVq5%7E8QabDfK60nWuA10CodvlaRDqVpuYEAvF2n5tY3Adf6-V-YdcaxE2DTlHXm65oJsJwWJTGiQYzTtn4rEVWKgQHVYp7CqX0IdyaILr966agOZvdUGDUZfkZtG6E9A6zKOgOBfdpJn1tjmMKEkDscDvLJvg8r9QJY7yttPHOMNVruzVtoLjpg1lFb-tXco3h%7EFZVKiOIZL%7E597WbaDu8hdZOQ__&Key-Pair-Id=KVTP0A1DKRTAX [following]\n",
+            "--2023-11-28 19:52:23--  https://cdn-lfs.huggingface.co/repos/12/2b/122bd8e9eccbb3acc98acf73e0ecef3c96f24dcdb5f6639074ed304eb19f9cd4/76c55033c6b2b1cc3f62513458f84748a23352495fd42b1062a7401de5ff9bd9?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27gpt-4_single.jsonl%3B+filename%3D%22gpt-4_single.jsonl%22%3B&Expires=1701460343&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcwMTQ2MDM0M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8xMi8yYi8xMjJiZDhlOWVjY2JiM2FjYzk4YWNmNzNlMGVjZWYzYzk2ZjI0ZGNkYjVmNjYzOTA3NGVkMzA0ZWIxOWY5Y2Q0Lzc2YzU1MDMzYzZiMmIxY2MzZjYyNTEzNDU4Zjg0NzQ4YTIzMzUyNDk1ZmQ0MmIxMDYyYTc0MDFkZTVmZjliZDk%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=hwTqBVlLz755xHaQaN6cSDP2FxoPBAXFcOE2uvFAYzg0Y90kGkY3A74Fj2wAkToA-dN1WJeMc%7Ef2XarD%7EbAw%7E4v2JCw9kphUxL-pcRF1uNBI2pzS-3Joff-m%7Ee3GVq5%7E8QabDfK60nWuA10CodvlaRDqVpuYEAvF2n5tY3Adf6-V-YdcaxE2DTlHXm65oJsJwWJTGiQYzTtn4rEVWKgQHVYp7CqX0IdyaILr966agOZvdUGDUZfkZtG6E9A6zKOgOBfdpJn1tjmMKEkDscDvLJvg8r9QJY7yttPHOMNVruzVtoLjpg1lFb-tXco3h%7EFZVKiOIZL%7E597WbaDu8hdZOQ__&Key-Pair-Id=KVTP0A1DKRTAX\n",
+            "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 18.65.25.40, 18.65.25.122, 18.65.25.124, ...\n",
+            "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|18.65.25.40|:443... connected.\n",
+            "HTTP request sent, awaiting response... 200 OK\n",
+            "Length: 20113128 (19M) [text/plain]\n",
+            "Saving to: ‘gpt-4_single.jsonl’\n",
+            "\n",
+            "gpt-4_single.jsonl  100%[===================>]  19.18M  25.8MB/s    in 0.7s    \n",
+            "\n",
+            "2023-11-28 19:52:25 (25.8 MB/s) - ‘gpt-4_single.jsonl’ saved [20113128/20113128]\n",
+            "\n",
+            "--2023-11-28 19:52:25--  https://huggingface.co/spaces/lmsys/mt-bench/resolve/main/data/mt_bench/model_judgment/gpt-4_pair.jsonl\n",
+            "Resolving huggingface.co (huggingface.co)... 18.164.174.55, 18.164.174.23, 18.164.174.118, ...\n",
+            "Connecting to huggingface.co (huggingface.co)|18.164.174.55|:443... connected.\n",
+            "HTTP request sent, awaiting response... 302 Found\n",
+            "Location: https://cdn-lfs.huggingface.co/repos/12/2b/122bd8e9eccbb3acc98acf73e0ecef3c96f24dcdb5f6639074ed304eb19f9cd4/d662c0b7d1d297f0494fcb4cc09fe8f054fa22d75deb4754a483a921984bc585?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27gpt-4_pair.jsonl%3B+filename%3D%22gpt-4_pair.jsonl%22%3B&Expires=1701460345&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcwMTQ2MDM0NX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8xMi8yYi8xMjJiZDhlOWVjY2JiM2FjYzk4YWNmNzNlMGVjZWYzYzk2ZjI0ZGNkYjVmNjYzOTA3NGVkMzA0ZWIxOWY5Y2Q0L2Q2NjJjMGI3ZDFkMjk3ZjA0OTRmY2I0Y2MwOWZlOGYwNTRmYTIyZDc1ZGViNDc1NGE0ODNhOTIxOTg0YmM1ODU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=RcHQsWboSyCegZB6o-k6-9fsGpTmhArmdubGyrc7VTT2cc9FKMoPc4vHW0RtMgS%7EkYWm2eA9sfex%7EWN%7E5A0i1CBBWP3EDq365Jt52BdOw4BbOtezicyT2eLPzNkgrw3RuLMZTApHUr6md1TVm0W15rmSaUpoQT5sKcVwq%7EvmmLXr6AFOV6vWho6vEHSadzT8GJkK%7El9xOtBGhCE-pWOsEU6siX9sw0HwZBmg1mcXJzMj2du%7Em5AmG3lXsJm2fFY0ZmhSZjm7FH%7EBxF38wTuuf3gBUeJUU%7Ecx0Lv935FSAmmdzqrXO4CiGq%7EQSTp7uga8mUJikosX6DlfLMZudAIVzg__&Key-Pair-Id=KVTP0A1DKRTAX [following]\n",
+            "--2023-11-28 19:52:25--  https://cdn-lfs.huggingface.co/repos/12/2b/122bd8e9eccbb3acc98acf73e0ecef3c96f24dcdb5f6639074ed304eb19f9cd4/d662c0b7d1d297f0494fcb4cc09fe8f054fa22d75deb4754a483a921984bc585?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27gpt-4_pair.jsonl%3B+filename%3D%22gpt-4_pair.jsonl%22%3B&Expires=1701460345&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcwMTQ2MDM0NX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8xMi8yYi8xMjJiZDhlOWVjY2JiM2FjYzk4YWNmNzNlMGVjZWYzYzk2ZjI0ZGNkYjVmNjYzOTA3NGVkMzA0ZWIxOWY5Y2Q0L2Q2NjJjMGI3ZDFkMjk3ZjA0OTRmY2I0Y2MwOWZlOGYwNTRmYTIyZDc1ZGViNDc1NGE0ODNhOTIxOTg0YmM1ODU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=RcHQsWboSyCegZB6o-k6-9fsGpTmhArmdubGyrc7VTT2cc9FKMoPc4vHW0RtMgS%7EkYWm2eA9sfex%7EWN%7E5A0i1CBBWP3EDq365Jt52BdOw4BbOtezicyT2eLPzNkgrw3RuLMZTApHUr6md1TVm0W15rmSaUpoQT5sKcVwq%7EvmmLXr6AFOV6vWho6vEHSadzT8GJkK%7El9xOtBGhCE-pWOsEU6siX9sw0HwZBmg1mcXJzMj2du%7Em5AmG3lXsJm2fFY0ZmhSZjm7FH%7EBxF38wTuuf3gBUeJUU%7Ecx0Lv935FSAmmdzqrXO4CiGq%7EQSTp7uga8mUJikosX6DlfLMZudAIVzg__&Key-Pair-Id=KVTP0A1DKRTAX\n",
+            "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 18.65.25.40, 18.65.25.122, 18.65.25.124, ...\n",
+            "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|18.65.25.40|:443... connected.\n",
+            "HTTP request sent, awaiting response... 200 OK\n",
+            "Length: 48043462 (46M) [binary/octet-stream]\n",
+            "Saving to: ‘gpt-4_pair.jsonl’\n",
+            "\n",
+            "gpt-4_pair.jsonl    100%[===================>]  45.82M  36.0MB/s    in 1.3s    \n",
+            "\n",
+            "2023-11-28 19:52:27 (36.0 MB/s) - ‘gpt-4_pair.jsonl’ saved [48043462/48043462]\n",
+            "\n"
+          ]
+        }
+      ],
+      "source": [
+        "!wget https://huggingface.co/spaces/lmsys/mt-bench/resolve/main/data/mt_bench/model_judgment/gpt-4_single.jsonl\n",
+        "!wget https://huggingface.co/spaces/lmsys/mt-bench/resolve/main/data/mt_bench/model_judgment/gpt-4_pair.jsonl"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install -U plotly kaleido"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "4eYlKr9RrPu2",
+        "outputId": "b957d1f9-0024-4c5c-eb07-dcb1a0071081"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: plotly in /usr/local/lib/python3.10/dist-packages (5.15.0)\n",
+            "Collecting plotly\n",
+            "  Downloading plotly-5.18.0-py3-none-any.whl (15.6 MB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.6/15.6 MB\u001b[0m \u001b[31m27.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hCollecting kaleido\n",
+            "  Downloading kaleido-0.2.1-py2.py3-none-manylinux1_x86_64.whl (79.9 MB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.9/79.9 MB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly) (8.2.3)\n",
+            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from plotly) (23.2)\n",
+            "Installing collected packages: kaleido, plotly\n",
+            "  Attempting uninstall: plotly\n",
+            "    Found existing installation: plotly 5.15.0\n",
+            "    Uninstalling plotly-5.15.0:\n",
+            "      Successfully uninstalled plotly-5.15.0\n",
+            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
+            "lida 0.0.10 requires fastapi, which is not installed.\n",
+            "lida 0.0.10 requires python-multipart, which is not installed.\n",
+            "lida 0.0.10 requires uvicorn, which is not installed.\u001b[0m\u001b[31m\n",
+            "\u001b[0mSuccessfully installed kaleido-0.2.1 plotly-5.18.0\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import json\n",
+        "import pandas as pd\n",
+        "import plotly.express as px\n",
+        "import plotly.graph_objects as go\n",
+        "\n",
+        "\n",
+        "CATEGORIES = [\"Writing\", \"Roleplay\", \"Reasoning\", \"Math\", \"Coding\", \"Extraction\", \"STEM\", \"Humanities\"]\n",
+        "\n",
+        "\n",
+        "def get_model_df():\n",
+        "    cnt = 0\n",
+        "    q2result = []\n",
+        "    fin = open(\"gpt-4_single.jsonl\", \"r\")\n",
+        "    for line in fin:\n",
+        "        obj = json.loads(line)\n",
+        "        obj[\"category\"] = CATEGORIES[(obj[\"question_id\"]-81)//10]\n",
+        "        q2result.append(obj)\n",
+        "    df = pd.DataFrame(q2result)\n",
+        "    return df\n",
+        "\n",
+        "def toggle(res_str):\n",
+        "    if res_str == \"win\":\n",
+        "        return \"loss\"\n",
+        "    elif res_str == \"loss\":\n",
+        "        return \"win\"\n",
+        "    return \"tie\"\n",
+        "\n",
+        "def get_model_df_pair():\n",
+        "    fin = open(\"gpt-4_pair.jsonl\", \"r\")\n",
+        "    cnt = 0\n",
+        "    q2result = []\n",
+        "    for line in fin:\n",
+        "        obj = json.loads(line)\n",
+        "\n",
+        "        result = {}\n",
+        "        result[\"qid\"] = str(obj[\"question_id\"])\n",
+        "        result[\"turn\"] = str(obj[\"turn\"])\n",
+        "        if obj[\"g1_winner\"] == \"model_1\" and obj[\"g2_winner\"] == \"model_1\":\n",
+        "            result[\"result\"] = \"win\"\n",
+        "        elif obj[\"g1_winner\"] == \"model_2\" and obj[\"g2_winner\"] == \"model_2\":\n",
+        "            result[\"result\"] = \"loss\"\n",
+        "        else:\n",
+        "            result[\"result\"] = \"tie\"\n",
+        "        result[\"category\"] = CATEGORIES[(obj[\"question_id\"]-81)//10]\n",
+        "        result[\"model\"] = obj[\"model_1\"]\n",
+        "        q2result.append(result)\n",
+        "\n",
+        "    df = pd.DataFrame(q2result)\n",
+        "\n",
+        "    return df\n",
+        "\n",
+        "df = get_model_df()\n",
+        "df_pair = get_model_df_pair()"
+      ],
+      "metadata": {
+        "id": "m2tG_vDyqWZw"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df_pair"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 423
+        },
+        "id": "wUw1sxfmaGuK",
+        "outputId": "21365f64-c2fa-47c7-9ad4-ca114eac6533"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      qid turn result    category         model\n",
+              "0      81    1   loss     Writing    alpaca-13b\n",
+              "1      81    2   loss     Writing    alpaca-13b\n",
+              "2      82    1   loss     Writing    alpaca-13b\n",
+              "3      82    2   loss     Writing    alpaca-13b\n",
+              "4      83    1   loss     Writing    alpaca-13b\n",
+              "...   ...  ...    ...         ...           ...\n",
+              "4795  158    2    tie  Humanities  wizardlm-30b\n",
+              "4796  159    1   loss  Humanities  wizardlm-30b\n",
+              "4797  159    2    win  Humanities  wizardlm-30b\n",
+              "4798  160    1   loss  Humanities  wizardlm-30b\n",
+              "4799  160    2    tie  Humanities  wizardlm-30b\n",
+              "\n",
+              "[4800 rows x 5 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-28f6ebcf-4509-4c45-8fe3-2d64ca044a2f\" class=\"colab-df-container\">\n",
+              "    <div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>qid</th>\n",
+              "      <th>turn</th>\n",
+              "      <th>result</th>\n",
+              "      <th>category</th>\n",
+              "      <th>model</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>81</td>\n",
+              "      <td>1</td>\n",
+              "      <td>loss</td>\n",
+              "      <td>Writing</td>\n",
+              "      <td>alpaca-13b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>81</td>\n",
+              "      <td>2</td>\n",
+              "      <td>loss</td>\n",
+              "      <td>Writing</td>\n",
+              "      <td>alpaca-13b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>82</td>\n",
+              "      <td>1</td>\n",
+              "      <td>loss</td>\n",
+              "      <td>Writing</td>\n",
+              "      <td>alpaca-13b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>82</td>\n",
+              "      <td>2</td>\n",
+              "      <td>loss</td>\n",
+              "      <td>Writing</td>\n",
+              "      <td>alpaca-13b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>83</td>\n",
+              "      <td>1</td>\n",
+              "      <td>loss</td>\n",
+              "      <td>Writing</td>\n",
+              "      <td>alpaca-13b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4795</th>\n",
+              "      <td>158</td>\n",
+              "      <td>2</td>\n",
+              "      <td>tie</td>\n",
+              "      <td>Humanities</td>\n",
+              "      <td>wizardlm-30b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4796</th>\n",
+              "      <td>159</td>\n",
+              "      <td>1</td>\n",
+              "      <td>loss</td>\n",
+              "      <td>Humanities</td>\n",
+              "      <td>wizardlm-30b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4797</th>\n",
+              "      <td>159</td>\n",
+              "      <td>2</td>\n",
+              "      <td>win</td>\n",
+              "      <td>Humanities</td>\n",
+              "      <td>wizardlm-30b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4798</th>\n",
+              "      <td>160</td>\n",
+              "      <td>1</td>\n",
+              "      <td>loss</td>\n",
+              "      <td>Humanities</td>\n",
+              "      <td>wizardlm-30b</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4799</th>\n",
+              "      <td>160</td>\n",
+              "      <td>2</td>\n",
+              "      <td>tie</td>\n",
+              "      <td>Humanities</td>\n",
+              "      <td>wizardlm-30b</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>4800 rows × 5 columns</p>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-28f6ebcf-4509-4c45-8fe3-2d64ca044a2f')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-28f6ebcf-4509-4c45-8fe3-2d64ca044a2f button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-28f6ebcf-4509-4c45-8fe3-2d64ca044a2f');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "<div id=\"df-02d34fc9-f4ca-40d7-b50a-bd1ffede5665\">\n",
+              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-02d34fc9-f4ca-40d7-b50a-bd1ffede5665')\"\n",
+              "            title=\"Suggest charts\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "     width=\"24px\">\n",
+              "    <g>\n",
+              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+              "    </g>\n",
+              "</svg>\n",
+              "  </button>\n",
+              "\n",
+              "<style>\n",
+              "  .colab-df-quickchart {\n",
+              "      --bg-color: #E8F0FE;\n",
+              "      --fill-color: #1967D2;\n",
+              "      --hover-bg-color: #E2EBFA;\n",
+              "      --hover-fill-color: #174EA6;\n",
+              "      --disabled-fill-color: #AAA;\n",
+              "      --disabled-bg-color: #DDD;\n",
+              "  }\n",
+              "\n",
+              "  [theme=dark] .colab-df-quickchart {\n",
+              "      --bg-color: #3B4455;\n",
+              "      --fill-color: #D2E3FC;\n",
+              "      --hover-bg-color: #434B5C;\n",
+              "      --hover-fill-color: #FFFFFF;\n",
+              "      --disabled-bg-color: #3B4455;\n",
+              "      --disabled-fill-color: #666;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart {\n",
+              "    background-color: var(--bg-color);\n",
+              "    border: none;\n",
+              "    border-radius: 50%;\n",
+              "    cursor: pointer;\n",
+              "    display: none;\n",
+              "    fill: var(--fill-color);\n",
+              "    height: 32px;\n",
+              "    padding: 0;\n",
+              "    width: 32px;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart:hover {\n",
+              "    background-color: var(--hover-bg-color);\n",
+              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "    fill: var(--button-hover-fill-color);\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart-complete:disabled,\n",
+              "  .colab-df-quickchart-complete:disabled:hover {\n",
+              "    background-color: var(--disabled-bg-color);\n",
+              "    fill: var(--disabled-fill-color);\n",
+              "    box-shadow: none;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-spinner {\n",
+              "    border: 2px solid var(--fill-color);\n",
+              "    border-color: transparent;\n",
+              "    border-bottom-color: var(--fill-color);\n",
+              "    animation:\n",
+              "      spin 1s steps(1) infinite;\n",
+              "  }\n",
+              "\n",
+              "  @keyframes spin {\n",
+              "    0% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "      border-left-color: var(--fill-color);\n",
+              "    }\n",
+              "    20% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    30% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    40% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    60% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    80% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "    90% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "  }\n",
+              "</style>\n",
+              "\n",
+              "  <script>\n",
+              "    async function quickchart(key) {\n",
+              "      const quickchartButtonEl =\n",
+              "        document.querySelector('#' + key + ' button');\n",
+              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
+              "      try {\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      } catch (error) {\n",
+              "        console.error('Error during call to suggestCharts:', error);\n",
+              "      }\n",
+              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+              "    }\n",
+              "    (() => {\n",
+              "      let quickchartButtonEl =\n",
+              "        document.querySelector('#df-02d34fc9-f4ca-40d7-b50a-bd1ffede5665 button');\n",
+              "      quickchartButtonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "    })();\n",
+              "  </script>\n",
+              "</div>\n",
+              "    </div>\n",
+              "  </div>\n"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 4
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "all_models = df[\"model\"].unique()\n",
+        "print(all_models)\n",
+        "scores_all = []\n",
+        "for model in all_models:\n",
+        "    for cat in CATEGORIES:\n",
+        "        # filter category/model, and score format error (<1% case)\n",
+        "        res = df[(df[\"category\"]==cat) & (df[\"model\"]==model) & (df[\"score\"] >= 0)]\n",
+        "        score = res[\"score\"].mean()\n",
+        "\n",
+        "        # # pairwise result\n",
+        "        # res_pair = df_pair[(df_pair[\"category\"]==cat) & (df_pair[\"model\"]==model)][\"result\"].value_counts()\n",
+        "        # wincnt = res_pair[\"win\"] if \"win\" in res_pair.index else 0\n",
+        "        # tiecnt = res_pair[\"tie\"] if \"tie\" in res_pair.index else 0\n",
+        "        # winrate = wincnt/res_pair.sum()\n",
+        "        # winrate_adjusted = (wincnt + tiecnt)/res_pair.sum()\n",
+        "        # # print(winrate_adjusted)\n",
+        "\n",
+        "        # scores_all.append({\"model\": model, \"category\": cat, \"score\": score, \"winrate\": winrate, \"wtrate\": winrate_adjusted})\n",
+        "        scores_all.append({\"model\": model, \"category\": cat, \"score\": score})"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "MpBKLuVmqZ7O",
+        "outputId": "f7ea476f-dde8-4b7c-fb69-5d7d33999caf"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "['alpaca-13b' 'baize-v2-13b' 'chatglm-6b' 'claude-instant-v1' 'claude-v1'\n",
+            " 'dolly-v2-12b' 'falcon-40b-instruct' 'fastchat-t5-3b' 'gpt-3.5-turbo'\n",
+            " 'gpt-4' 'gpt4all-13b-snoozy' 'guanaco-33b' 'guanaco-65b'\n",
+            " 'h2ogpt-oasst-open-llama-13b' 'koala-13b' 'llama-13b' 'mpt-30b-chat'\n",
+            " 'mpt-30b-instruct' 'mpt-7b-chat' 'nous-hermes-13b'\n",
+            " 'oasst-sft-4-pythia-12b' 'oasst-sft-7-llama-30b' 'palm-2-chat-bison-001'\n",
+            " 'rwkv-4-raven-14b' 'stablelm-tuned-alpha-7b' 'tulu-30b' 'vicuna-13b-v1.3'\n",
+            " 'vicuna-33b-v1.3' 'vicuna-7b-v1.3' 'wizardlm-13b' 'wizardlm-30b'\n",
+            " 'Llama-2-7b-chat' 'Llama-2-13b-chat' 'Llama-2-70b-chat']\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "target_models = [\"Llama-2-7b-chat\", \"Llama-2-13b-chat\", \"Llama-2-70b-chat\", \"gpt-3.5-turbo\", \"claude-v1\", \"gpt-4\"]\n",
+        "\n",
+        "scores_target = [scores_all[i] for i in range(len(scores_all)) if scores_all[i][\"model\"] in target_models]\n",
+        "\n",
+        "# sort by target_models\n",
+        "scores_target = sorted(scores_target, key=lambda x: target_models.index(x[\"model\"]), reverse=True)\n",
+        "\n",
+        "df_score = pd.DataFrame(scores_target)\n",
+        "df_score = df_score[df_score[\"model\"].isin(target_models)]\n",
+        "\n",
+        "rename_map = {\"llama-13b\": \"LLaMA-13B\",\n",
+        "              \"alpaca-13b\": \"Alpaca-13B\",\n",
+        "              \"vicuna-33b-v1.3\": \"Vicuna-33B\",\n",
+        "              \"vicuna-13b-v1.3\": \"Vicuna-13B\",\n",
+        "              \"gpt-3.5-turbo\": \"GPT-3.5-turbo\",\n",
+        "              \"claude-v1\": \"Claude-v1\",\n",
+        "              \"gpt-4\": \"GPT-4\"}\n",
+        "\n",
+        "for k, v in rename_map.items():\n",
+        "    df_score.replace(k, v, inplace=True)\n",
+        "\n",
+        "fig = px.line_polar(df_score, r = 'score', theta = 'category', line_close = True, category_orders = {\"category\": CATEGORIES},\n",
+        "                    color = 'model', markers=True, color_discrete_sequence=px.colors.qualitative.Pastel)\n",
+        "\n",
+        "fig.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 542
+        },
+        "id": "5i8R0l-XqkgO",
+        "outputId": "10151ab6-cf3d-4162-a0cf-c510f2e3968a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/html": [
+              "<html>\n",
+              "<head><meta charset=\"utf-8\" /></head>\n",
+              "<body>\n",
+              "    <div>            <script src=\"https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/MathJax.js?config=TeX-AMS-MML_SVG\"></script><script type=\"text/javascript\">if (window.MathJax && window.MathJax.Hub && window.MathJax.Hub.Config) {window.MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}</script>                <script type=\"text/javascript\">window.PlotlyConfig = {MathJaxConfig: 'local'};</script>\n",
+              "        <script charset=\"utf-8\" src=\"https://cdn.plot.ly/plotly-2.27.0.min.js\"></script>                <div id=\"7d62e79f-72ea-4c66-9a41-d7c4c2f7d741\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"7d62e79f-72ea-4c66-9a41-d7c4c2f7d741\")) {                    Plotly.newPlot(                        \"7d62e79f-72ea-4c66-9a41-d7c4c2f7d741\",                        [{\"hovertemplate\":\"model=GPT-4\\u003cbr\\u003escore=%{r}\\u003cbr\\u003ecategory=%{theta}\\u003cextra\\u003e\\u003c\\u002fextra\\u003e\",\"legendgroup\":\"GPT-4\",\"line\":{\"color\":\"rgb(102, 197, 204)\",\"dash\":\"solid\"},\"marker\":{\"symbol\":\"circle\"},\"mode\":\"markers+lines\",\"name\":\"GPT-4\",\"r\":[9.65,8.9,9.0,6.8,8.55,9.375,9.7,9.95,9.65],\"showlegend\":true,\"subplot\":\"polar\",\"theta\":[\"Writing\",\"Roleplay\",\"Reasoning\",\"Math\",\"Coding\",\"Extraction\",\"STEM\",\"Humanities\",\"Writing\"],\"type\":\"scatterpolar\"},{\"hovertemplate\":\"model=Claude-v1\\u003cbr\\u003escore=%{r}\\u003cbr\\u003ecategory=%{theta}\\u003cextra\\u003e\\u003c\\u002fextra\\u003e\",\"legendgroup\":\"Claude-v1\",\"line\":{\"color\":\"rgb(246, 207, 113)\",\"dash\":\"solid\"},\"marker\":{\"symbol\":\"circle\"},\"mode\":\"markers+lines\",\"name\":\"Claude-v1\",\"r\":[9.5,8.5,5.95,4.8,6.25,8.8,9.7,9.7,9.5],\"showlegend\":true,\"subplot\":\"polar\",\"theta\":[\"Writing\",\"Roleplay\",\"Reasoning\",\"Math\",\"Coding\",\"Extraction\",\"STEM\",\"Humanities\",\"Writing\"],\"type\":\"scatterpolar\"},{\"hovertemplate\":\"model=GPT-3.5-turbo\\u003cbr\\u003escore=%{r}\\u003cbr\\u003ecategory=%{theta}\\u003cextra\\u003e\\u003c\\u002fextra\\u003e\",\"legendgroup\":\"GPT-3.5-turbo\",\"line\":{\"color\":\"rgb(248, 156, 116)\",\"dash\":\"solid\"},\"marker\":{\"symbol\":\"circle\"},\"mode\":\"markers+lines\",\"name\":\"GPT-3.5-turbo\",\"r\":[9.2,8.4,5.65,6.3,6.9,8.85,8.7,9.55,9.2],\"showlegend\":true,\"subplot\":\"polar\",\"theta\":[\"Writing\",\"Roleplay\",\"Reasoning\",\"Math\",\"Coding\",\"Extraction\",\"STEM\",\"Humanities\",\"Writing\"],\"type\":\"scatterpolar\"},{\"hovertemplate\":\"model=Llama-2-70b-chat\\u003cbr\\u003escore=%{r}\\u003cbr\\u003ecategory=%{theta}\\u003cextra\\u003e\\u003c\\u002fextra\\u003e\",\"legendgroup\":\"Llama-2-70b-chat\",\"line\":{\"color\":\"rgb(220, 176, 242)\",\"dash\":\"solid\"},\"marker\":{\"symbol\":\"circle\"},\"mode\":\"markers+lines\",\"name\":\"Llama-2-70b-chat\",\"r\":[9.3,7.5,5.8,3.3,3.15,7.25,8.925,9.625,9.3],\"showlegend\":true,\"subplot\":\"polar\",\"theta\":[\"Writing\",\"Roleplay\",\"Reasoning\",\"Math\",\"Coding\",\"Extraction\",\"STEM\",\"Humanities\",\"Writing\"],\"type\":\"scatterpolar\"},{\"hovertemplate\":\"model=Llama-2-13b-chat\\u003cbr\\u003escore=%{r}\\u003cbr\\u003ecategory=%{theta}\\u003cextra\\u003e\\u003c\\u002fextra\\u003e\",\"legendgroup\":\"Llama-2-13b-chat\",\"line\":{\"color\":\"rgb(135, 197, 95)\",\"dash\":\"solid\"},\"marker\":{\"symbol\":\"circle\"},\"mode\":\"markers+lines\",\"name\":\"Llama-2-13b-chat\",\"r\":[8.85,7.5,5.1,3.45,3.0,6.925,8.625,9.75,8.85],\"showlegend\":true,\"subplot\":\"polar\",\"theta\":[\"Writing\",\"Roleplay\",\"Reasoning\",\"Math\",\"Coding\",\"Extraction\",\"STEM\",\"Humanities\",\"Writing\"],\"type\":\"scatterpolar\"},{\"hovertemplate\":\"model=Llama-2-7b-chat\\u003cbr\\u003escore=%{r}\\u003cbr\\u003ecategory=%{theta}\\u003cextra\\u003e\\u003c\\u002fextra\\u003e\",\"legendgroup\":\"Llama-2-7b-chat\",\"line\":{\"color\":\"rgb(158, 185, 243)\",\"dash\":\"solid\"},\"marker\":{\"symbol\":\"circle\"},\"mode\":\"markers+lines\",\"name\":\"Llama-2-7b-chat\",\"r\":[8.9,7.7,4.25,2.4,3.0,6.5,8.65,8.75,8.9],\"showlegend\":true,\"subplot\":\"polar\",\"theta\":[\"Writing\",\"Roleplay\",\"Reasoning\",\"Math\",\"Coding\",\"Extraction\",\"STEM\",\"Humanities\",\"Writing\"],\"type\":\"scatterpolar\"}],                        {\"template\":{\"data\":{\"histogram2dcontour\":[{\"type\":\"histogram2dcontour\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"choropleth\":[{\"type\":\"choropleth\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"histogram2d\":[{\"type\":\"histogram2d\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"heatmap\":[{\"type\":\"heatmap\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"heatmapgl\":[{\"type\":\"heatmapgl\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"contourcarpet\":[{\"type\":\"contourcarpet\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"contour\":[{\"type\":\"contour\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"surface\":[{\"type\":\"surface\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"mesh3d\":[{\"type\":\"mesh3d\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"scatter\":[{\"fillpattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2},\"type\":\"scatter\"}],\"parcoords\":[{\"type\":\"parcoords\",\"line\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterpolargl\":[{\"type\":\"scatterpolargl\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"bar\":[{\"error_x\":{\"color\":\"#2a3f5f\"},\"error_y\":{\"color\":\"#2a3f5f\"},\"marker\":{\"line\":{\"color\":\"#E5ECF6\",\"width\":0.5},\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"bar\"}],\"scattergeo\":[{\"type\":\"scattergeo\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterpolar\":[{\"type\":\"scatterpolar\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"histogram\":[{\"marker\":{\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"histogram\"}],\"scattergl\":[{\"type\":\"scattergl\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatter3d\":[{\"type\":\"scatter3d\",\"line\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}},\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scattermapbox\":[{\"type\":\"scattermapbox\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterternary\":[{\"type\":\"scatterternary\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scattercarpet\":[{\"type\":\"scattercarpet\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"carpet\":[{\"aaxis\":{\"endlinecolor\":\"#2a3f5f\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"minorgridcolor\":\"white\",\"startlinecolor\":\"#2a3f5f\"},\"baxis\":{\"endlinecolor\":\"#2a3f5f\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"minorgridcolor\":\"white\",\"startlinecolor\":\"#2a3f5f\"},\"type\":\"carpet\"}],\"table\":[{\"cells\":{\"fill\":{\"color\":\"#EBF0F8\"},\"line\":{\"color\":\"white\"}},\"header\":{\"fill\":{\"color\":\"#C8D4E3\"},\"line\":{\"color\":\"white\"}},\"type\":\"table\"}],\"barpolar\":[{\"marker\":{\"line\":{\"color\":\"#E5ECF6\",\"width\":0.5},\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"barpolar\"}],\"pie\":[{\"automargin\":true,\"type\":\"pie\"}]},\"layout\":{\"autotypenumbers\":\"strict\",\"colorway\":[\"#636efa\",\"#EF553B\",\"#00cc96\",\"#ab63fa\",\"#FFA15A\",\"#19d3f3\",\"#FF6692\",\"#B6E880\",\"#FF97FF\",\"#FECB52\"],\"font\":{\"color\":\"#2a3f5f\"},\"hovermode\":\"closest\",\"hoverlabel\":{\"align\":\"left\"},\"paper_bgcolor\":\"white\",\"plot_bgcolor\":\"#E5ECF6\",\"polar\":{\"bgcolor\":\"#E5ECF6\",\"angularaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"radialaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"}},\"ternary\":{\"bgcolor\":\"#E5ECF6\",\"aaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"baxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"caxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"}},\"coloraxis\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}},\"colorscale\":{\"sequential\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]],\"sequentialminus\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]],\"diverging\":[[0,\"#8e0152\"],[0.1,\"#c51b7d\"],[0.2,\"#de77ae\"],[0.3,\"#f1b6da\"],[0.4,\"#fde0ef\"],[0.5,\"#f7f7f7\"],[0.6,\"#e6f5d0\"],[0.7,\"#b8e186\"],[0.8,\"#7fbc41\"],[0.9,\"#4d9221\"],[1,\"#276419\"]]},\"xaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\",\"title\":{\"standoff\":15},\"zerolinecolor\":\"white\",\"automargin\":true,\"zerolinewidth\":2},\"yaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\",\"title\":{\"standoff\":15},\"zerolinecolor\":\"white\",\"automargin\":true,\"zerolinewidth\":2},\"scene\":{\"xaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2},\"yaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2},\"zaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2}},\"shapedefaults\":{\"line\":{\"color\":\"#2a3f5f\"}},\"annotationdefaults\":{\"arrowcolor\":\"#2a3f5f\",\"arrowhead\":0,\"arrowwidth\":1},\"geo\":{\"bgcolor\":\"white\",\"landcolor\":\"#E5ECF6\",\"subunitcolor\":\"white\",\"showland\":true,\"showlakes\":true,\"lakecolor\":\"white\"},\"title\":{\"x\":0.05},\"mapbox\":{\"style\":\"light\"}}},\"polar\":{\"domain\":{\"x\":[0.0,1.0],\"y\":[0.0,1.0]},\"angularaxis\":{\"direction\":\"clockwise\",\"rotation\":90,\"categoryorder\":\"array\",\"categoryarray\":[\"Writing\",\"Roleplay\",\"Reasoning\",\"Math\",\"Coding\",\"Extraction\",\"STEM\",\"Humanities\"]}},\"legend\":{\"title\":{\"text\":\"model\"},\"tracegroupgap\":0},\"margin\":{\"t\":60}},                        {\"responsive\": true}                    ).then(function(){\n",
+              "                            \n",
+              "var gd = document.getElementById('7d62e79f-72ea-4c66-9a41-d7c4c2f7d741');\n",
+              "var x = new MutationObserver(function (mutations, observer) {{\n",
+              "        var display = window.getComputedStyle(gd).display;\n",
+              "        if (!display || display === 'none') {{\n",
+              "            console.log([gd, 'removed!']);\n",
+              "            Plotly.purge(gd);\n",
+              "            observer.disconnect();\n",
+              "        }}\n",
+              "}});\n",
+              "\n",
+              "// Listen for the removal of the full notebook cells\n",
+              "var notebookContainer = gd.closest('#notebook-container');\n",
+              "if (notebookContainer) {{\n",
+              "    x.observe(notebookContainer, {childList: true});\n",
+              "}}\n",
+              "\n",
+              "// Listen for the clearing of the current output cell\n",
+              "var outputEl = gd.closest('.output');\n",
+              "if (outputEl) {{\n",
+              "    x.observe(outputEl, {childList: true});\n",
+              "}}\n",
+              "\n",
+              "                        })                };                            </script>        </div>\n",
+              "</body>\n",
+              "</html>"
+            ]
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# fig = px.line_polar(df_score, r = 'wtrate', theta = 'category', line_close = True, category_orders = {\"category\": CATEGORIES},\n",
+        "#                     color = 'model', markers=True, color_discrete_sequence=px.colors.qualitative.Pastel)\n",
+        "# fig.show()"
+      ],
+      "metadata": {
+        "id": "MaBaUN4IqvJI"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "fig.update_layout(\n",
+        "    font=dict(\n",
+        "        size=18,\n",
+        "    ),\n",
+        ")\n",
+        "fig.write_image(\"fig.png\", width=800, height=600, scale=2)"
+      ],
+      "metadata": {
+        "id": "4l1bzYM2bgDW"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "nfpERnxFANhV"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}