List your company

Output Ranking on ProductBench Home & Kitchen

95Top-5 AccuracyCORE-Reasoning
47.6859.96572.2584.535Feb 3, 2026

Evaluation results

MethodLinks
CORE-ReasoningModel=Claude-42026.02959083.5
CORE-ReviewModel=Gemini-2.52026.0294.589.583.5
CORE-ReviewModel=Claude-42026.0293.58982
CORE-ReasoningModel=GPT-4o2026.02928781
CORE-ReviewModel=Grok-32026.0290.58578.5
CORE-ReviewModel=GPT-4o2026.0289.58579
CORE-ReasoningModel=Gemini-2.52026.0288.58477.5
CORE-ReasoningModel=Grok-32026.02888377
RAFModel=GPT-4o2026.02786144
RAFModel=Claude-42026.0276.56448.5
SRPModel=Claude-42026.027559.543.5
SRPModel=GPT-4o2026.0272.55842
RAFModel=Grok-32026.0271.553.541
RAFModel=Gemini-2.52026.02705746
SRPModel=Gemini-2.52026.026854.540
SRPModel=Grok-32026.0265.55238.5
TAPModel=Claude-42026.0262.548.534.5
TAPModel=GPT-4o2026.026147.534
CORE-StringModel=Claude-42026.025846.534
STSModel=Claude-42026.02574533.5
CORE-StringModel=GPT-4o2026.025545.533
STSModel=GPT-4o2026.02544432.5
CORE-StringModel=Gemini-2.52026.0253.54331
STSModel=Gemini-2.52026.025342.531.5
STSModel=Grok-32026.02524230
CORE-StringModel=Grok-32026.0251.54230.5
TAPModel=Grok-32026.025040.529.5
TAPModel=Gemini-2.52026.0249.539.529.5