Our new X account is live! Follow @wizwand_team for updates

Promotion Success Rate on Tools & Home Improvement

95.5Top-5 Accuracy

CORE-Review

Updated 4d ago

Evaluation Results

Method	Links
CORE-Review 2026.02		95.5	90.5	83.5
CORE-Review 2026.02		95	90	84
CORE-Reasoning 2026.02		93	88	82.5
CORE-Reasoning 2026.02		92.5	88	81
CORE-Review 2026.02		90	85.5	80
CORE-Reasoning 2026.02		89.5	84	78.5
CORE-Review 2026.02		88	83.5	77
CORE-Reasoning 2026.02		87	83	77
RAF 2026.02		81	67.5	50.5
RAF 2026.02		79.5	63.5	46.5
SRP 2026.02		77	61	45
SRP 2026.02		74	59	43
RAF 2026.02		72	54	40.5
RAF 2026.02		70	51.5	41.5
SRP 2026.02		66	51	36.5
SRP 2026.02		64	49.5	35.5
TAP 2026.02		63.5	48.5	34.5
TAP 2026.02		61	47	33
CORE-String 2026.02		57.5	46	33.5
CORE-String 2026.02		54.5	44	32.5
CORE-String 2026.02		52.5	42.5	31
CORE-String 2026.02		52	42.5	31
STS 2026.02		52	41	29
STS 2026.02		49	39	27.5
STS 2026.02		48	38	26
STS 2026.02		47	37	25
TAP 2026.02		45	35	23
TAP 2026.02		44	34	23.5