data_dir/elo_ranks.jsonl

{"model name ": "gpt-4-0125-preview", "elo overall": 1309, "# battles": 5429}
{"model name ": "claude-3-opus-20240229", "elo overall": 1155, "# battles": 2366}
{"model name ": "claude-3-sonnet-20240229", "elo overall": 1140, "# battles": 2608}
{"model name ": "mistral-large-2402", "elo overall": 1120, "# battles": 1881}
{"model name ": "Mistral-7B-Instruct-v0.2", "elo overall": 1102, "# battles": 2371}
{"model name ": "gemini-1.0-pro", "elo overall": 1073, "# battles": 1815}
{"model name ": "Mixtral-8x7B-Instruct-v0.1", "elo overall": 1069, "# battles": 3417}
{"model name ": "Yi-34B-Chat", "elo overall": 1058, "# battles": 2428}
{"model name ": "Llama-2-70b-chat-hf.nosp", "elo overall": 1031, "# battles": 1942}
{"model name ": "Llama-2-13b-chat-hf.nosp", "elo overall": 1007, "# battles": 1888}
{"model name ": "tulu-2-dpo-70b", "elo overall": 997, "# battles": 3435}
{"model name ": "zephyr-7b-beta", "elo overall": 986, "# battles": 3367}
{"model name ": "Llama-2-7b-chat-hf.nosp", "elo overall": 984, "# battles": 1898}
{"model name ": "gpt-3.5-turbo-0125", "elo overall": 983, "# battles": 14003}
{"model name ": "gemma-7b-it", "elo overall": 951, "# battles": 2518}
{"model name ": "command", "elo overall": 948, "# battles": 1733}
{"model name ": "Llama-2-70b-chat-hf", "elo overall": 890, "# battles": 2391}
{"model name ": "gemma-2b-it", "elo overall": 874, "# battles": 2484}
{"model name ": "Llama-2-13b-chat-hf", "elo overall": 860, "# battles": 2350}
{"model name ": "vicuna-13b-v1.5", "elo overall": 847, "# battles": 2478}
{"model name ": "Mistral-7B-Instruct-v0.1", "elo overall": 821, "# battles": 2479}
{"model name ": "Llama-2-7b-chat-hf", "elo overall": 806, "# battles": 2297}