# Meme Classification and Explanation on ArMeme Source: [Meme Classification and Explanation on ArMeme]() Collection index: [llms.txt]() Data updated: 2026-06-16T08:09:33.479Z Evaluation of model performance on the ArMeme dataset for the combined task of Meme Classification and Explanation. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Meme Classification and Explanation | | Dataset (including any stated split) | ArMeme | | Metric | Accuracy (Acc) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy (Acc)](): Higher is better; unit: PERCENT. - [Weighted F1 Score (W-F1)](): Higher is better; unit: PERCENT. - [Macro F1 Score (M-F1)](): Higher is better; unit: PERCENT. - [BS Score](): Higher is better; unit: PERCENT. - [Metric Score (Met)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Acc) | Result date | Report paper | | --- | --- | --- | --- | | GPT-4.1 | 69.7 | Not recorded | 6a30d8c1d33dfb23e783cdde | | GPT-4.1 | 68.7 | Not recorded | 6a30d8c1d33dfb23e783cdde | | L4-Scout | 67.9 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Gemma | 67.5 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Qwen-I | 64.6 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Fanar-2-Oryx-IVU | 64.4 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Qwen-T | 63.1 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Fanar-2-Oryx-IVU | 57.3 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Kimi-T | 57.2 | Not recorded | 6a30d8c1d33dfb23e783cdde | | L4-Scout | 54.1 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Kimi-I | 39.9 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Llama | 35.3 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Qwen-I | 30.2 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Gemma | 28.5 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Kimi-T | 28.3 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Qwen-T | 22.1 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Kimi-I | 21.8 | Not recorded | 6a30d8c1d33dfb23e783cdde | | Llama | 7 | Not recorded | 6a30d8c1d33dfb23e783cdde | ### GPT-4.1 Accuracy (Acc): 69.7. Result ID: 6a3103dffbc373592c2d1a8f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Strategy":"Standard"}. This record does not assert independent reproduction. ### GPT-4.1 Accuracy (Acc): 68.7. Result ID: 6a3103dffbc373592c2d1a8e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Strategy":"CoT"}. This record does not assert independent reproduction. ### L4-Scout Accuracy (Acc): 67.9. Result ID: 6a3103dffbc373592c2d1a8c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Strategy":"CoT","Backbone":"Llama-4-Scout-17B"}. This record does not assert independent reproduction. ### Gemma Accuracy (Acc): 67.5. Result ID: 6a3103dffbc373592c2d1a8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"CoT","Backbone":"Gemma-3-12B"}. This record does not assert independent reproduction. ### Qwen-I Accuracy (Acc): 64.6. Result ID: 6a3103dffbc373592c2d1a86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"CoT","Model Type":"Instruct","Backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### Fanar-2-Oryx-IVU Accuracy (Acc): 64.4. Result ID: 6a3103dffbc373592c2d1a94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"CoT"}. This record does not assert independent reproduction. ### Qwen-T Accuracy (Acc): 63.1. Result ID: 6a3103dffbc373592c2d1a88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"CoT","Model Type":"Thinking","Backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### Fanar-2-Oryx-IVU Accuracy (Acc): 57.3. Result ID: 6a3103dffbc373592c2d1a95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"Standard"}. This record does not assert independent reproduction. ### Kimi-T Accuracy (Acc): 57.2. Result ID: 6a3103dffbc373592c2d1a92. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"CoT","Model Type":"Thinking","Backbone":"Kimi-VL-A3B"}. This record does not assert independent reproduction. ### L4-Scout Accuracy (Acc): 54.1. Result ID: 6a3103dffbc373592c2d1a8d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Strategy":"Standard","Backbone":"Llama-4-Scout-17B"}. This record does not assert independent reproduction. ### Kimi-I Accuracy (Acc): 39.9. Result ID: 6a3103dffbc373592c2d1a90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"CoT","Model Type":"Instruct","Backbone":"Kimi-VL-A3B"}. This record does not assert independent reproduction. ### Llama Accuracy (Acc): 35.3. Result ID: 6a3103dffbc373592c2d1a84. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Strategy":"CoT","Backbone":"Llama-3.2-11B"}. This record does not assert independent reproduction. ### Qwen-I Accuracy (Acc): 30.2. Result ID: 6a3103dffbc373592c2d1a87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"Standard","Model Type":"Instruct","Backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### Gemma Accuracy (Acc): 28.5. Result ID: 6a3103dffbc373592c2d1a8b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"Standard","Backbone":"Gemma-3-12B"}. This record does not assert independent reproduction. ### Kimi-T Accuracy (Acc): 28.3. Result ID: 6a3103dffbc373592c2d1a93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"Standard","Model Type":"Thinking","Backbone":"Kimi-VL-A3B"}. This record does not assert independent reproduction. ### Qwen-T Accuracy (Acc): 22.1. Result ID: 6a3103dffbc373592c2d1a89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"Standard","Model Type":"Thinking","Backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### Kimi-I Accuracy (Acc): 21.8. Result ID: 6a3103dffbc373592c2d1a91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Strategy":"Standard","Model Type":"Instruct","Backbone":"Kimi-VL-A3B"}. This record does not assert independent reproduction. ### Llama Accuracy (Acc): 7. Result ID: 6a3103dffbc373592c2d1a85. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Strategy":"Standard","Backbone":"Llama-3.2-11B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.