AHA-Memes: leaderboard
AHA-Memes (2026) is a multimodal benchmark for hate in Arabic memes with human gold labels. This board is zero-shot binary hateful versus not-hateful macro-F1 in percent on the 5K gold test split, given each meme image with its OCR text; higher is better.
Metric: Binary hateful versus not-hateful macro-F1 (%), zero-shot on the 5K human-annotated gold test split of Arabic memes (image with its OCR text); higher is better. Source: arxiv.org. Saturation forecast: Around June 2028. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 71.1 | #266 |
| 2 | Qwen 3 VL 8B Instruct | 64.3 | #981 |
| 3 | GPT-5 | 62.8 | #167 |
| 4 | Gemini 3.5 Flash | 49.9 | #101 |
| 5 | Qwen 3 VL 8B (Thinking) | 46.9 | #887 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=aha-memes · How It Works · Data refreshed daily, snapshot 2026-11-13.