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

Multi-choice Evaluation on BQD

99.33p+

SFT

Updated 4d ago

Evaluation Results

Method	Links
SFT 2026.04		99.33	32	65.67
SFT 2026.04		98.67	94.67	96.67
PFT 2026.04		98.67	94.67	96.67
CPO 2026.04		97.67	35	66.33
CPO 2026.04		96.67	93.33	95
DPO 2026.04		96	42.67	69.33
DPO 2026.04		95.33	92.67	94
Base 2026.04		84.67	58	71.33
DPO 2026.04		84	42	63
PFT 2026.04		83.33	71.33	77.33
DPO 2026.04		75.33	66.67	71
CPO 2026.04		73	67.5	70.25
DPO 2026.04		72.67	38	55.33
PFT 2026.04		72.67	66.67	69.67
CAA 2026.04		71.67	51.83	61.75
Base 2026.04		70	57.33	63.67
SFT 2026.04		70	66	68
CPO 2026.04		69.33	35.67	52.5
SFT 2026.04		68	33.33	50.67
CAA 2026.04		66.73	50.73	58.73
Base 2026.04		64	56	60
DPO 2026.04		64	62	63
CAA 2026.04		61.97	56	69.18
CAA 2026.04		61.87	56.17	69.18
CPO 2026.04		58.67	60.5	59.58
DPO 2026.04		58.67	68	63.33
DPO 2026.04		56.67	72.67	64.67
CAA 2026.04		54.07	43.87	48.97
CPO 2026.04		54	60.33	57.17
SFT 2026.04		52.67	58.67	55.67
CPO 2026.04		52	85.33	68.67
SFT 2026.04		50	54	52
CAA 2026.04		49.33	52.23	50.78
CPO 2026.04		48.67	32.5	40.58
SFT 2026.04		48	94.67	71.33
SFT 2026.04		46	31.33	38.67
CPO 2026.04		38	50.12	44.06
SFT 2026.04		36	48.67	42.33
DPO 2026.04		28	65.33	46.67