Meme Classification and Explanation on ArMeme
69.7Accuracy (Acc)GPT-4.1
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GPT-4.1Prompting Strategy=Standard2026.06 | 69.7 | 61.9 | 35 | 63.7 | 18 | |
| GPT-4.1Prompting Strategy=CoT2026.06 | 68.7 | 59.9 | 29 | 57.7 | 8.3 | |
| L4-ScoutPrompting Strategy=CoT, Backbone=Llama-4-Scout-17B2026.06 | 67.9 | 58.2 | 28.4 | 58.9 | 9.3 | |
| GemmaPrompting Strategy=CoT, Backbone=Gemma-3-12B2026.06 | 67.5 | 62.5 | 34.5 | 59.7 | 10.3 | |
| Qwen-IPrompting Strategy=CoT, Model Type=Instruct, Backbone=Qwen3-VL-8B2026.06 | 64.6 | 62.6 | 38.8 | 62.7 | 21 | |
| Fanar-2-Oryx-IVUPrompting Strategy=CoT2026.06 | 64.4 | 59.3 | 33 | 58.2 | 9.1 | |
| Qwen-TPrompting Strategy=CoT, Model Type=Thinking, Backbone=Qwen3-VL-8B2026.06 | 63.1 | 56.1 | 28.1 | 59.8 | 17.3 | |
| Fanar-2-Oryx-IVUPrompting Strategy=Standard2026.06 | 57.3 | 50.4 | 24 | 61.4 | 16.1 | |
| Kimi-TPrompting Strategy=CoT, Model Type=Thinking, Backbone=Kimi-VL-A3B2026.06 | 57.2 | 56.2 | 31 | 58.6 | 11.5 | |
| L4-ScoutPrompting Strategy=Standard, Backbone=Llama-4-Scout-17B2026.06 | 54.1 | 56.9 | 34 | 64.9 | 27.6 | |
| Kimi-IPrompting Strategy=CoT, Model Type=Instruct, Backbone=Kimi-VL-A3B2026.06 | 39.9 | 43.7 | 23.5 | 60.2 | 13.4 | |
| LlamaPrompting Strategy=CoT, Backbone=Llama-3.2-11B2026.06 | 35.3 | 40.1 | 21.6 | 56.3 | 13.1 | |
| Qwen-IPrompting Strategy=Standard, Model Type=Instruct, Backbone=Qwen3-VL-8B2026.06 | 30.2 | 37.3 | 25.9 | 61.6 | 19.9 | |
| GemmaPrompting Strategy=Standard, Backbone=Gemma-3-12B2026.06 | 28.5 | 19.7 | 15.5 | 62.7 | 21.3 | |
| Kimi-TPrompting Strategy=Standard, Model Type=Thinking, Backbone=Kimi-VL-A3B2026.06 | 28.3 | 33.6 | 21.7 | 61.1 | 22.2 | |
| Qwen-TPrompting Strategy=Standard, Model Type=Thinking, Backbone=Qwen3-VL-8B2026.06 | 22.1 | 10.8 | 16.8 | 60.1 | 20.7 | |
| Kimi-IPrompting Strategy=Standard, Model Type=Instruct, Backbone=Kimi-VL-A3B2026.06 | 21.8 | 26.3 | 17.6 | 61.8 | 20 | |
| LlamaPrompting Strategy=Standard, Backbone=Llama-3.2-11B2026.06 | 7 | 4.8 | 6.1 | 59.1 | 15.7 |