open-r1-eval-leaderboard
/
eval_results
/mistralai
/Mistral-7B-Instruct-v0.2
/main
/alpaca_eval
/results_2024-04-30T20-33-21.json
{ | |
"results":{ | |
"mistralai_Mistral-7B-Instruct-v0.2_main":{ | |
"win_rate":15.2711510391, | |
"standard_error":1.0767080244, | |
"n_wins":111, | |
"n_wins_base":694, | |
"n_draws":0, | |
"n_total":805, | |
"discrete_win_rate":13.7888198758, | |
"mode":"community", | |
"avg_length":1644, | |
"length_controlled_winrate":18.5902533119 | |
} | |
} | |
} |