open-r1-eval-leaderboard
/
eval_results
/HuggingFaceH4
/zephyr-7b-beta
/main
/alpaca_eval
/results_2024-04-30T20-39-34.json
{ | |
"results":{ | |
"HuggingFaceH4_zephyr-7b-beta_main":{ | |
"win_rate":11.2437731314, | |
"standard_error":0.9855834906, | |
"n_wins":89, | |
"n_wins_base":716, | |
"n_draws":0, | |
"n_total":805, | |
"discrete_win_rate":11.0559006211, | |
"mode":"community", | |
"avg_length":1525, | |
"length_controlled_winrate":12.7627754026 | |
} | |
} | |
} |