Humor Generation on Electronic Sheep (test)
1.8Visual Understanding Avg RankHOMER
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| HOMER2026.02 | 1.8 | 1.4 | 1.5 | 0.98 | 92.2 | |
| CLoT2026.02 | 3.5 | 3.2 | 2.7 | 0.83 | 78.9 | |
| CoT2026.02 | 3.8 | 4.3 | 4.2 | 0.88 | 84.2 | |
| Self-Consistency2026.02 | 4.2 | 4.5 | 4.8 | 0.84 | 86.4 | |
| Few-Shot2026.02 | 4.5 | 4.5 | 4.1 | 0.89 | 83.1 | |
| LoL2026.02 | 4.5 | 4.6 | 5.7 | 0.94 | 91.9 | |
| Phunny2026.02 | 6.8 | 6.8 | 6.9 | 0.89 | 85.2 | |
| HumorousAI2026.02 | 6.9 | 6.7 | 6.1 | 0.92 | 88.5 |