Share your thoughts, 1 month free Claude Pro on usSee more

Reasoning on In-distribution reasoning (test)

29.01GPQA Score

AutoSelection

Updated 2mo ago

Evaluation Results

Method	Links
AutoSelection 2026.05		29.01	54.58	30	55.33	42.23
Varentropy 2026.05		28.12	49.2	35.21	61.27	43.45
AutoSelection 2026.05		26.78	11.52	6.08	34.55	19.73
N-gram 2026.05		24.77	10.76	3.26	34.55	18.34
N-gram 2026.05		24.1	51.63	19.13	57.38	38.06
AO 2026.05		23.66	49.81	33.36	55.33	40.54
Full data 2026.05		23.66	64.82	31.95	61	45.36
MONA 2026.05		23.66	70.58	28.69	61.83	46.19
SemDedup 2026.05		23.66	60.19	29.23	61.88	43.74
Random 2026.05		23.43	52.23	27.39	56.83	39.97
IFD 2026.05		23.21	23.88	24.45	56.22	31.94
AO 2026.05		23.21	62.69	35.86	60.11	45.47
AutoSelection 2026.05		22.99	72.78	36.84	63.72	49.08
Random 2026.05		21.87	64.59	31.73	61.94	45.03
AO 2026.05		21.43	9.55	9.04	33.33	18.34
Random 2026.05		21.43	64.44	30.22	62	44.52
IFD 2026.05		21.42	21.22	21.84	60.66	31.29
N-gram 2026.05		21.42	59.66	21.63	61.11	40.96
Full data 2026.05		21.2	55.26	22.93	55.94	38.83
Random 2026.05		21.2	52.16	27.82	56.38	39.39
MONA 2026.05		21.2	54.35	24.89	55.77	39.05
Varentropy 2026.05		20.31	38.51	25.76	55.5	35.02
Random 2026.05		19.41	14.1	8.47	33.33	18.83
MONA 2026.05		18.97	10.38	9.89	33.61	18.21
SemDedup 2026.05		17.41	6.36	0.76	26.77	12.83
Full data 2026.05		17.19	16.6	4.78	33.06	17.91
Varentropy 2026.05		17.18	3.56	8.69	31.05	15.12
IFD 2026.05		16.07	10.08	4.34	29.33	14.96
Random 2026.05		15.62	13.49	9.45	32.33	17.72
SemDedup 2026.05		14.73	40.4	20.43	56.88	33.11