open-r1-eval-leaderboard
/
eval_results
/meta-llama
/Meta-Llama-3-8B-Instruct
/main
/alpaca_eval
/results_2024-05-25T10-32-20.json
{ | |
"results":{ | |
"meta-llama_Meta-Llama-3-8B-Instruct_main":{ | |
"win_rate":23.5610261449, | |
"standard_error":1.2717601154, | |
"n_wins":172, | |
"n_wins_base":632, | |
"n_draws":1, | |
"n_total":805, | |
"discrete_win_rate":21.4285714286, | |
"mode":"community", | |
"avg_length":1977, | |
"length_controlled_winrate":22.9661788667 | |
} | |
} | |
} |