data_dir/elo_ranks.all.jsonl

{"model name ": "gpt-4-0125-preview", "elo overall": 1309, "Information seeking": 1282, "Creative Writing": 1267, "Coding & Debugging": 1376, "Reasoning": 1366, "Editing": 1211, "Math": 1276, "Planning": 1299, "Brainstorming": 1322, "Role playing": 1240, "Advice seeking": 1295, "Data Analysis": 1286, "Others": 1068, "average": 1274.0, "# battles": 5429}
{"model name ": "claude-3-opus-20240229", "elo overall": 1155, "Information seeking": 1131, "Creative Writing": 1066, "Coding & Debugging": 1282, "Reasoning": 1204, "Editing": 1146, "Math": 1160, "Planning": 1159, "Brainstorming": 1111, "Role playing": 964, "Advice seeking": 1114, "Data Analysis": 1151, "Others": 1031, "average": 1126.5833333333333, "# battles": 2366}
{"model name ": "claude-3-sonnet-20240229", "elo overall": 1140, "Information seeking": 1115, "Creative Writing": 1081, "Coding & Debugging": 1247, "Reasoning": 1170, "Editing": 1152, "Math": 1142, "Planning": 1163, "Brainstorming": 1092, "Role playing": 1005, "Advice seeking": 1081, "Data Analysis": 1170, "Others": 1014, "average": 1119.3333333333333, "# battles": 2608}
{"model name ": "mistral-large-2402", "elo overall": 1120, "Information seeking": 1090, "Creative Writing": 1107, "Coding & Debugging": 1155, "Reasoning": 1136, "Editing": 1097, "Math": 1092, "Planning": 1081, "Brainstorming": 1078, "Role playing": 1067, "Advice seeking": 1060, "Data Analysis": 1097, "Others": 1021, "average": 1090.0833333333333, "# battles": 1881}
{"model name ": "Mistral-7B-Instruct-v0.2", "elo overall": 1102, "Information seeking": 1084, "Creative Writing": 1138, "Coding & Debugging": 1140, "Reasoning": 1047, "Editing": 1105, "Math": 1021, "Planning": 1090, "Brainstorming": 1076, "Role playing": 1118, "Advice seeking": 1067, "Data Analysis": 1058, "Others": 1002, "average": 1078.8333333333333, "# battles": 2371}
{"model name ": "gemini-1.0-pro", "elo overall": 1073, "Information seeking": 1089, "Creative Writing": 1040, "Coding & Debugging": 1083, "Reasoning": 1067, "Editing": 1021, "Math": 1063, "Planning": 1067, "Brainstorming": 1023, "Role playing": 1032, "Advice seeking": 1072, "Data Analysis": 1090, "Others": 1007, "average": 1054.5, "# battles": 1815}
{"model name ": "Mixtral-8x7B-Instruct-v0.1", "elo overall": 1069, "Information seeking": 1079, "Creative Writing": 1050, "Coding & Debugging": 1125, "Reasoning": 1063, "Editing": 1018, "Math": 1061, "Planning": 1004, "Brainstorming": 1026, "Role playing": 1080, "Advice seeking": 1005, "Data Analysis": 1060, "Others": 993, "average": 1047.0, "# battles": 3417}
{"model name ": "Yi-34B-Chat", "elo overall": 1058, "Information seeking": 1072, "Creative Writing": 1105, "Coding & Debugging": 939, "Reasoning": 1073, "Editing": 1042, "Math": 1011, "Planning": 1094, "Brainstorming": 1140, "Role playing": 1071, "Advice seeking": 1087, "Data Analysis": 943, "Others": 997, "average": 1047.8333333333333, "# battles": 2428}
{"model name ": "Llama-2-70b-chat-hf.nosp", "elo overall": 1031, "Information seeking": 1092, "Creative Writing": 1065, "Coding & Debugging": 883, "Reasoning": 1022, "Editing": 987, "Math": 975, "Planning": 1003, "Brainstorming": 1049, "Role playing": 1070, "Advice seeking": 1036, "Data Analysis": 959, "Others": 1020, "average": 1013.4166666666666, "# battles": 1942}
{"model name ": "Llama-2-13b-chat-hf.nosp", "elo overall": 1007, "Information seeking": 1056, "Creative Writing": 1058, "Coding & Debugging": 850, "Reasoning": 975, "Editing": 986, "Math": 947, "Planning": 984, "Brainstorming": 1041, "Role playing": 1053, "Advice seeking": 1008, "Data Analysis": 912, "Others": 1014, "average": 990.3333333333334, "# battles": 1888}
{"model name ": "tulu-2-dpo-70b", "elo overall": 997, "Information seeking": 1003, "Creative Writing": 1024, "Coding & Debugging": 939, "Reasoning": 993, "Editing": 980, "Math": 975, "Planning": 965, "Brainstorming": 941, "Role playing": 1065, "Advice seeking": 976, "Data Analysis": 932, "Others": 991, "average": 982.0, "# battles": 3435}
{"model name ": "zephyr-7b-beta", "elo overall": 986, "Information seeking": 1002, "Creative Writing": 991, "Coding & Debugging": 991, "Reasoning": 962, "Editing": 981, "Math": 941, "Planning": 967, "Brainstorming": 936, "Role playing": 1022, "Advice seeking": 938, "Data Analysis": 1003, "Others": 962, "average": 974.6666666666666, "# battles": 3367}
{"model name ": "Llama-2-7b-chat-hf.nosp", "elo overall": 984, "Information seeking": 1033, "Creative Writing": 1026, "Coding & Debugging": 843, "Reasoning": 962, "Editing": 963, "Math": 908, "Planning": 987, "Brainstorming": 1003, "Role playing": 1048, "Advice seeking": 1020, "Data Analysis": 934, "Others": 1011, "average": 978.1666666666666, "# battles": 1898}
{"model name ": "gpt-3.5-turbo-0125", "elo overall": 983, "Information seeking": 935, "Creative Writing": 934, "Coding & Debugging": 1155, "Reasoning": 1018, "Editing": 994, "Math": 1148, "Planning": 986, "Brainstorming": 929, "Role playing": 924, "Advice seeking": 961, "Data Analysis": 1071, "Others": 977, "average": 1002.6666666666666, "# battles": 14003}
{"model name ": "gemma-7b-it", "elo overall": 951, "Information seeking": 931, "Creative Writing": 938, "Coding & Debugging": 993, "Reasoning": 957, "Editing": 928, "Math": 985, "Planning": 981, "Brainstorming": 984, "Role playing": 954, "Advice seeking": 973, "Data Analysis": 979, "Others": 992, "average": 966.25, "# battles": 2518}
{"model name ": "command", "elo overall": 948, "Information seeking": 939, "Creative Writing": 942, "Coding & Debugging": 969, "Reasoning": 925, "Editing": 943, "Math": 940, "Planning": 979, "Brainstorming": 988, "Role playing": 948, "Advice seeking": 964, "Data Analysis": 966, "Others": 979, "average": 956.8333333333334, "# battles": 1733}
{"model name ": "Llama-2-70b-chat-hf", "elo overall": 890, "Information seeking": 902, "Creative Writing": 902, "Coding & Debugging": 824, "Reasoning": 903, "Editing": 949, "Math": 896, "Planning": 907, "Brainstorming": 946, "Role playing": 905, "Advice seeking": 946, "Data Analysis": 927, "Others": 999, "average": 917.1666666666666, "# battles": 2391}
{"model name ": "gemma-2b-it", "elo overall": 874, "Information seeking": 843, "Creative Writing": 898, "Coding & Debugging": 894, "Reasoning": 829, "Editing": 888, "Math": 896, "Planning": 906, "Brainstorming": 919, "Role playing": 906, "Advice seeking": 891, "Data Analysis": 914, "Others": 977, "average": 896.75, "# battles": 2484}
{"model name ": "Llama-2-13b-chat-hf", "elo overall": 860, "Information seeking": 878, "Creative Writing": 866, "Coding & Debugging": 802, "Reasoning": 883, "Editing": 955, "Math": 915, "Planning": 897, "Brainstorming": 891, "Role playing": 865, "Advice seeking": 938, "Data Analysis": 885, "Others": 1007, "average": 898.5, "# battles": 2350}
{"model name ": "vicuna-13b-v1.5", "elo overall": 847, "Information seeking": 849, "Creative Writing": 862, "Coding & Debugging": 817, "Reasoning": 847, "Editing": 870, "Math": 897, "Planning": 830, "Brainstorming": 873, "Role playing": 911, "Advice seeking": 852, "Data Analysis": 879, "Others": 973, "average": 871.6666666666666, "# battles": 2478}
{"model name ": "Mistral-7B-Instruct-v0.1", "elo overall": 821, "Information seeking": 790, "Creative Writing": 800, "Coding & Debugging": 947, "Reasoning": 798, "Editing": 871, "Math": 892, "Planning": 806, "Brainstorming": 783, "Role playing": 892, "Advice seeking": 823, "Data Analysis": 922, "Others": 968, "average": 857.6666666666666, "# battles": 2479}
{"model name ": "Llama-2-7b-chat-hf", "elo overall": 806, "Information seeking": 805, "Creative Writing": 834, "Coding & Debugging": 754, "Reasoning": 806, "Editing": 917, "Math": 856, "Planning": 836, "Brainstorming": 856, "Role playing": 853, "Advice seeking": 883, "Data Analysis": 861, "Others": 997, "average": 854.8333333333334, "# battles": 2297}