,win_rate,standard_error,mode,avg_length,n_wins,n_wins_base,n_draws,n_total,discrete_win_rate,length_controlled_winrate,lc_standard_error | |
Tucano-1b1-DPO,15.419484227948896,1.160056594824009,community,1667,124,681,0,805,15.403726708074533,8.800275585416614,0.08352323105119325 | |
Tucano-1b1-Instruct,7.893483774877183,0.830060323275043,community,1075,58,747,0,805,7.204968944099378,6.376247766233091,0.07082994421269635 |