List your company

Multimodal Humor Explanation on New Yorker

76.7PrecisionCOT
47.99655.44862.970.352Feb 22, 2025

Evaluation results

MethodLinks
COTModel=Flash1.52025.0276.713.122.3
ZSModel=Flash1.52025.0276.624.136.6
BOTTLEHUMORModel=Flash1.52025.0276.224.136.7
COTModel=GPT4o2025.027626.138.8
ZSModel=GPT4o2025.0275.44253.9
SR-noCModel=GPT4o2025.0275.245.856.9
SRModel=GPT4o2025.0275.144.656
BOTTLEHUMORModel=GPT4o2025.0274.547.758.2
SR-noCModel=Flash1.52025.027421.232.9
SRModel=Flash1.52025.0273.722.934.9
COTModel=Qwen22025.0270.91119
BOTTLEHUMORModel=Qwen22025.0268.417.728.1
SRModel=Qwen22025.0267.417.828.2
SR-noCModel=Qwen22025.0267.318.629.1
ZSModel=Qwen22025.0266.719.430.1
COTModel=Phi2025.0257.48.514.8
BOTTLEHUMORModel=Phi2025.0255.81523.6
ZSModel=Phi2025.0251.214.823
SR-noCModel=Phi2025.0251.215.123.3
SRModel=Phi2025.0249.11320.6