Multimodal Humor Explanation on YesBut
77.3PrecisionCOT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| COTModel=Flash1.52025.02 | 77.3 | 16.4 | 27.1 | |
| ZSModel=Flash1.52025.02 | 74.5 | 28.5 | 41.1 | |
| COTModel=GPT4o2025.02 | 74.1 | 26.2 | 38.7 | |
| ZSModel=GPT4o2025.02 | 73.9 | 47.8 | 58 | |
| BOTTLEHUMORModel=GPT4o2025.02 | 73.8 | 51.2 | 60.4 | |
| BOTTLEHUMORModel=Flash1.52025.02 | 73.4 | 30.6 | 43.1 | |
| SRModel=Flash1.52025.02 | 72.7 | 28.9 | 41.3 | |
| SR-noCModel=GPT4o2025.02 | 72.4 | 46.3 | 56.5 | |
| COTModel=Qwen22025.02 | 72.2 | 13.6 | 22.7 | |
| SR-noCModel=Flash1.52025.02 | 71.3 | 26.5 | 38.5 | |
| SR-noCModel=Qwen22025.02 | 70.2 | 20.6 | 31.8 | |
| ZSModel=Qwen22025.02 | 70 | 19.7 | 30.7 | |
| BOTTLEHUMORModel=Qwen22025.02 | 69.8 | 22.1 | 33.5 | |
| SRModel=GPT4o2025.02 | 69.4 | 46.7 | 55.8 | |
| SRModel=Qwen22025.02 | 68.9 | 20.3 | 31.3 | |
| BOTTLEHUMORModel=Phi2025.02 | 57.6 | 20 | 29.7 | |
| COTModel=Phi2025.02 | 56.2 | 11.7 | 19.3 | |
| ZSModel=Phi2025.02 | 54.4 | 19.3 | 28.3 | |
| SR-noCModel=Phi2025.02 | 54.1 | 17.4 | 26.1 | |
| SRModel=Phi2025.02 | 52.5 | 17.2 | 25.8 |