open-r1-eval-leaderboard
/
eval_results
/meta-llama
/Meta-Llama-3-70B-Instruct
/main
/alpaca_eval
/results_2024-05-25T10-55-30.json
{ | |
"results":{ | |
"meta-llama_Meta-Llama-3-70B-Instruct_main":{ | |
"win_rate":38.3394711996, | |
"standard_error":1.4323630787, | |
"n_wins":299, | |
"n_wins_base":504, | |
"n_draws":2, | |
"n_total":805, | |
"discrete_win_rate":37.2670807453, | |
"mode":"community", | |
"avg_length":1995, | |
"length_controlled_winrate":38.6637658329 | |
} | |
} | |
} |