Culture-Aware Humorous Captioning Eastern Culture Context 1.0 (test)
7.51IRGPT-4o
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| GPT-4o2026.04 | 7.51 | 5.72 | 5.96 | 8.04 | 6.74 | 6.5 | 6.75 | |
| QwenVL+CLoT2026.04 | 7.26 | 3.75 | 3.56 | 7.76 | 4.8 | 4.1 | 5.2 | |
| gemini-3-flash-preview2026.04 | 7.23 | 5.23 | 5.89 | 8.01 | 6.83 | 6.17 | 6.56 | |
| Claude Sonnet 4.5_pred2026.04 | 7.21 | 5.11 | 5.72 | 7.97 | 6.78 | 6.16 | 6.49 | |
| cogvlm2-llama3-chat-19B2026.04 | 7.2 | 3.93 | 4.52 | 7.73 | 5.02 | 4.84 | 5.54 | |
| Qwen3-VL-8B-Instruct2026.04 | 7.17 | 5.22 | 5.73 | 7.87 | 6.63 | 6.28 | 6.48 | |
| CuHAlign2026.04 | 6.89 | 6.3 | 5.91 | 7.88 | 6.68 | 6.3 | 6.66 | |
| Qwen2.5-VL-7B-Instruct2026.04 | 6.88 | 4.19 | 4.87 | 7.74 | 5.39 | 5.31 | 5.73 | |
| InternVL3-8B-Instruct2026.04 | 6.83 | 4.79 | 5.24 | 7.78 | 6.1 | 5.78 | 6.09 | |
| MiniCPM-V 2.62026.04 | 6.52 | 3.8 | 4.37 | 7.15 | 4.87 | 4.61 | 5.22 | |
| LLaVA-OneVision-7B2026.04 | 6.03 | 3.15 | 3.4 | 6.6 | 3.69 | 3.74 | 4.44 | |
| GLM-4V-9B2026.04 | 5.42 | 3.01 | 3.37 | 6.62 | 2.72 | 3.14 | 4.05 | |
| MiniGPT-42026.04 | 4.88 | 2.41 | 2.52 | 5.73 | 1.9 | 2.32 | 3.29 |