model	pass1	pass@count	win_rate	count	SE(A)	SE_x(A)	SE_pred(A)
cwm-baseline-400	31.1	31.1	10.7	1	1.7	NaN	NaN
cwm-baseline-380	30.2	30.2	9.98	1	1.7	NaN	NaN
cwm-baseline-210	29.5	29.5	9.73	1	1.7	NaN	NaN
cwm-selfplay-280	29.5	29.5	9.88	1	1.7	NaN	NaN
cwm-baseline_360-409	29.5	45.4	9.47	5	1.7	1.3	1
cwm-baseline-370	29.4	29.4	9.16	1	1.7	NaN	NaN
cwm-baseline-340	29.3	29.3	9.52	1	1.7	NaN	NaN
cwm-selfplay-120	29	29	9.43	1	1.7	NaN	NaN
cwm-baseline_340-389	29	45.1	9.11	5	1.7	1.3	1
cwm-baseline-220	28.9	28.9	9.24	1	1.7	NaN	NaN
cwm-selfplay-150	28.9	28.9	9.13	1	1.7	NaN	NaN
cwm-baseline_350-399	28.8	44.3	9	5	1.7	1.3	1
cwm-selfplay-270	28.7	28.7	9.43	1	1.7	NaN	NaN
cwm-selfplay-220	28.6	28.6	8.61	1	1.7	NaN	NaN
cwm-baseline-270	28.6	28.6	8.68	1	1.7	NaN	NaN
cwm-selfplay_120-169	28.6	45.6	8.99	5	1.7	1.3	1
cwm-baseline_330-379	28.5	44.2	8.79	5	1.7	1.3	1
cwm-baseline-390	28.5	28.5	8.96	1	1.7	NaN	NaN
cwm-selfplay-160	28.5	28.5	8.68	1	1.7	NaN	NaN
cwm-selfplay-140	28.5	28.5	9.09	1	1.7	NaN	NaN
cwm-selfplay-260	28.5	28.5	8.81	1	1.7	NaN	NaN
cwm-selfplay_240-289	28.4	44.6	9.08	4	1.7	1.3	1.1
cwm-selfplay-80	28.3	28.3	8.48	1	1.7	NaN	NaN
cwm-selfplay-180	28.3	28.3	8.54	1	1.7	NaN	NaN
cwm-baseline-320	28.3	28.3	8.92	1	1.7	NaN	NaN
cwm-baseline-170	28.3	28.3	8.64	1	1.7	NaN	NaN
cwm-selfplay_140-189	28.3	44.9	8.69	5	1.7	1.3	1
cwm-baseline_320-369	28.3	44	8.74	5	1.7	1.3	1
cwm-baseline_210-259	28.2	45.4	8.85	5	1.7	1.3	1.1
cwm-selfplay_130-179	28.2	45.3	8.75	5	1.7	1.3	1
cwm-baseline-360	28.2	28.2	8.76	1	1.7	NaN	NaN
cwm-selfplay_110-159	28.1	44.9	8.75	5	1.7	1.3	1.1
cwm-baseline_310-359	28.1	44	8.62	5	1.7	1.3	1
cwm-selfplay_150-199	28	44.2	8.53	5	1.7	1.3	1
cwm-baseline_200-249	28	45.3	8.67	5	1.7	1.3	1.1
cwm-selfplay-130	28	28	8.82	1	1.7	NaN	NaN
cwm-baseline-130	28	28	8.11	1	1.7	NaN	NaN
cwm-baseline_190-239	28	45.3	8.65	5	1.7	1.3	1
cwm-selfplay_250-299	28	45.6	8.81	5	1.7	1.3	1.1
cwm-selfplay-320	27.9	27.9	8.97	1	1.7	NaN	NaN
cwm-baseline-230	27.9	27.9	8.72	1	1.7	NaN	NaN
cwm-baseline-290	27.9	27.9	8.47	1	1.7	NaN	NaN
cwm-baseline-140	27.9	27.9	8.74	1	1.7	NaN	NaN
cwm-selfplay_260-309	27.9	45.3	8.74	5	1.7	1.3	1.1
cwm-selfplay-40	27.8	27.8	8.24	1	1.7	NaN	NaN
cwm-baseline-350	27.8	27.8	8.34	1	1.7	NaN	NaN
cwm-baseline-330	27.8	27.8	8.37	1	1.7	NaN	NaN
cwm-selfplay_270-319	27.7	44.2	8.67	5	1.7	1.3	1.1
cwm-baseline_300-349	27.7	44.6	8.41	5	1.7	1.3	1
cwm-selfplay_160-209	27.7	43.4	8.37	5	1.7	1.3	1
cwm-selfplay_100-149	27.7	44.6	8.56	5	1.7	1.3	1.1
cwm-selfplay-60	27.6	27.6	8.04	1	1.7	NaN	NaN
cwm-baseline-280	27.6	27.6	8.72	1	1.7	NaN	NaN
cwm-selfplay_230-279	27.6	43.5	8.61	4	1.7	1.2	1.1
cwm-baseline-240	27.6	27.6	8.49	1	1.7	NaN	NaN
cwm-selfplay-370	27.6	27.6	8.32	1	1.7	NaN	NaN
cwm-selfplay-310	27.6	27.6	8.45	1	1.7	NaN	NaN
cwm-selfplay_220-269	27.6	42.7	8.4	4	1.7	1.3	1
cwm-baseline_180-229	27.6	44.5	8.34	5	1.7	1.3	1
cwm-selfplay_280-329	27.6	43.4	8.58	5	1.7	1.3	1.1
cwm-baseline-190	27.5	27.5	8.38	1	1.7	NaN	NaN
cwm-selfplay_80-129	27.5	43	8.27	5	1.7	1.3	1
cwm-baseline_170-219	27.5	43.6	8.22	5	1.7	1.3	1
cwm-baseline_270-319	27.5	43	8.23	5	1.7	1.3	1
cwm-baseline_290-339	27.4	43.9	8.2	5	1.7	1.3	1
cwm-selfplay_180-229	27.4	43.1	8.19	5	1.6	1.3	1
cwm-selfplay_90-139	27.4	43.9	8.34	5	1.6	1.3	1
cwm-baseline_280-329	27.4	43.4	8.27	5	1.6	1.3	1
cwm-baseline_220-269	27.4	43.8	8.29	5	1.6	1.3	1
cwm-selfplay-390	27.4	27.4	8.8	1	1.6	NaN	NaN
cwm-selfplay-170	27.4	27.4	8.23	1	1.6	NaN	NaN
cwm-baseline_230-279	27.3	43.1	8.18	5	1.6	1.3	1
cwm-baseline_250-299	27.3	43	8.18	5	1.6	1.3	1
cwm-baseline_130-179	27.3	43.5	8.15	5	1.6	1.3	1
cwm-baseline_240-289	27.3	42.8	8.18	5	1.6	1.3	1
cwm-baseline-310	27.2	27.2	8.16	1	1.6	NaN	NaN
cwm-selfplay-190	27.2	27.2	8.26	1	1.6	NaN	NaN
cwm-selfplay-90	27.2	27.2	7.97	1	1.6	NaN	NaN
cwm-baseline-250	27.2	27.2	8.28	1	1.6	NaN	NaN
cwm-selfplay_40-89	27.2	42.8	7.88	5	1.6	1.3	1
cwm-selfplay_170-219	27.2	42.4	8.11	5	1.6	1.3	1
cwm-selfplay_50-99	27.1	42.7	7.83	5	1.6	1.3	1
cwm-baseline_260-309	27.1	42.4	7.98	5	1.6	1.3	1
cwm-selfplay_60-109	27.1	42.4	7.91	5	1.6	1.3	1
cwm-selfplay_190-239	27.1	43.1	8.08	5	1.6	1.3	1
cwm-baseline_120-169	27	43.4	8.03	5	1.6	1.3	1
cwm-selfplay_200-249	27	41.7	8.04	4	1.6	1.3	1
cwm-selfplay_210-259	27	41.6	8.05	4	1.6	1.3	1
cwm-selfplay_290-339	26.9	42.8	8.19	5	1.6	1.3	1
cwm-baseline_160-209	26.9	43.4	7.95	5	1.6	1.3	1
cwm-selfplay-360	26.9	26.9	7.95	1	1.6	NaN	NaN
cwm-selfplay-200	26.9	26.9	8.36	1	1.6	NaN	NaN
cwm-baseline-120	26.9	26.9	8.02	1	1.6	NaN	NaN
cwm-baseline-160	26.9	26.9	8.38	1	1.6	NaN	NaN
cwm-selfplay_300-349	26.9	44	8.37	5	1.6	1.2	1.1
cwm-selfplay_360-409	26.9	41.9	8.09	4	1.6	1.3	1
cwm-selfplay_310-359	26.9	44.7	8.26	5	1.6	1.2	1.1
cwm-baseline_140-189	26.8	43	7.96	5	1.6	1.3	1
cwm-selfplay-100	26.8	26.8	8.2	1	1.6	NaN	NaN
cwm-selfplay-50	26.8	26.8	7.76	1	1.6	NaN	NaN
cwm-selfplay-250	26.8	26.8	8.38	1	1.6	NaN	NaN
cwm-selfplay_320-369	26.8	44.7	8.16	5	1.6	1.2	1.1
cwm-baseline_100-149	26.8	43	7.83	5	1.6	1.3	1
cwm-selfplay_70-119	26.8	42.1	7.8	5	1.6	1.3	1
cwm-baseline_150-199	26.8	43.5	7.89	5	1.6	1.3	1
cwm-selfplay_350-399	26.7	43.6	7.96	5	1.6	1.3	1
cwm-selfplay_330-379	26.7	43.9	8.03	5	1.6	1.3	1.1
cwm-baseline_110-159	26.7	42.5	7.77	5	1.6	1.3	1
cwm-selfplay_30-79	26.6	42.8	7.75	5	1.6	1.3	1
cwm-selfplay_340-389	26.5	43.8	7.93	5	1.6	1.2	1.1
cwm-selfplay-330	26.5	26.5	7.96	1	1.6	NaN	NaN
cwm-selfplay-230	26.5	26.5	7.98	1	1.6	NaN	NaN
cwm-baseline_90-139	26.5	42.8	7.71	5	1.6	1.3	1
cwm-selfplay-290	26.4	26.4	7.78	1	1.6	NaN	NaN
cwm-baseline-90	26.4	26.4	8.12	1	1.6	NaN	NaN
cwm-selfplay-340	26.4	26.4	8.66	1	1.6	NaN	NaN
cwm-selfplay-300	26.3	26.3	8.03	1	1.6	NaN	NaN
cwm-baseline-200	26.3	26.3	7.4	1	1.6	NaN	NaN
cwm-selfplay_20-69	26.2	42.5	7.61	5	1.6	1.2	1
cwm-baseline-300	26	26	7.31	1	1.6	NaN	NaN
cwm-selfplay-350	26	26	7.49	1	1.6	NaN	NaN
cwm-selfplay-110	26	26	7.48	1	1.6	NaN	NaN
cwm-selfplay-210	26	26	7.37	1	1.6	NaN	NaN
cwm-selfplay-380	25.7	25.7	7.46	1	1.6	NaN	NaN
cwm-baseline-180	25.7	25.7	7.17	1	1.6	NaN	NaN
cwm-baseline-100	25.7	25.7	7.39	1	1.6	NaN	NaN
cwm-baseline_80-129	25.6	42.1	7.4	5	1.6	1.2	1
cwm-selfplay-70	25.4	25.4	7.07	1	1.6	NaN	NaN
cwm-baseline-260	25.3	25.3	6.94	1	1.6	NaN	NaN
cwm-baseline-40	25.3	25.3	7.46	1	1.6	NaN	NaN
cwm-baseline-150	25.3	25.3	7.09	1	1.6	NaN	NaN
cwm-baseline_70-119	25.3	41.5	7.19	5	1.6	1.2	1
cwm-selfplay-30	25.2	25.2	7.85	1	1.6	NaN	NaN
cwm-baseline-110	25.2	25.2	7.09	1	1.6	NaN	NaN
cwm-baseline-70	25.2	25.2	6.98	1	1.6	NaN	NaN
cwm-selfplay_10-59	25	41.9	7.19	5	1.6	1.2	1.1
cwm-baseline_60-109	24.9	41.3	6.98	5	1.6	1.2	1
cwm-baseline_50-99	24.4	40.2	6.7	5	1.6	1.2	1
cwm-baseline_40-89	24.1	39.9	6.57	5	1.6	1.2	1
cwm-baseline-80	23.9	23.9	6.58	1	1.6	NaN	NaN
cwm-baseline_30-79	23.9	39.5	6.45	5	1.6	1.2	1
cwm-selfplay-20	23.4	23.4	6.39	1	1.6	NaN	NaN
cwm-baseline_20-69	23.3	39.4	6.22	5	1.6	1.2	1
cwm-baseline-60	23.3	23.3	6.03	1	1.6	NaN	NaN
cwm-baseline-30	23	23	5.96	1	1.6	NaN	NaN
cwm-baseline-50	23	23	6	1	1.6	NaN	NaN
cwm-baseline_10-59	22.8	39	6.1	5	1.6	1.2	1
cwm-baseline-20	22	22	5.83	1	1.5	NaN	NaN
cwm-selfplay-10	22	22	5.95	1	1.5	NaN	NaN
cwm-baseline-10	20.9	20.9	5.46	1	1.5	NaN	NaN