{"benchmark_id":"bbh_cot","size":6511,"models":45,"total_pairs":924,"close_pairs":158,"no_solve":76,"tau-":138,"SE(A)":{"count":45.0,"mean":0.0056004515,"std":0.0005202542,"min":0.0042969993,"25%":0.0051629618,"50%":0.0058323948,"75%":0.0060672268,"max":0.0061958905},"SE_x(A)":{"count":45.0,"mean":0.0040678078,"std":0.0008835066,"min":0.0020820017,"25%":0.003652554,"50%":0.0041265565,"75%":0.0044885517,"max":0.006139509},"SE_pred(A)":{"count":45.0,"mean":0.003560643,"std":0.0012955815,"min":0.0,"25%":0.0031823622,"50%":0.0040261332,"75%":0.0043997468,"max":0.0047437109},"SE(A-B)":{"count":158.0,"mean":0.0067715717,"std":0.000813145,"min":0.0046501747,"25%":0.0063544214,"50%":0.0069639673,"75%":0.0073946066,"max":0.0078537702},"SE_x(A-B)":{"count":158.0,"mean":0.0039685394,"std":0.0010447164,"min":0.0015233449,"25%":0.0031510524,"50%":0.0037786885,"75%":0.0045512036,"max":0.0062058258},"SE_pred(A-B)":{"count":158.0,"mean":0.0053491357,"std":0.0010348422,"min":0.0021678868,"25%":0.0045424085,"50%":0.0058078883,"75%":0.0061933551,"max":0.0066391463},"SE_signtest":{"count":158.0,"mean":0.0067763273,"std":0.000814001,"min":0.0046513607,"25%":0.006360414,"50%":0.0069736338,"75%":0.0073977697,"max":0.0078543144},"corr(A,B)":{"count":158.0,"mean":0.481792633,"std":0.1412054853,"min":0.1936287986,"25%":0.3660437671,"50%":0.467874956,"75%":0.6070467217,"max":0.7247624519},"sum(A!=B)":{"count":158.0,"mean":1974.5450484677,"std":440.9158447234,"min":917.1818181792,"25%":1715.2977272487,"50%":2061.6439393736,"75%":2320.0492424115,"max":2615.242424224}}
