AHA-Memes: leaderboard
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 2028. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 71.1 |
| 2 | Qwen 3 VL 8B Instruct | 64.3 |
| 3 | GPT-5 | 62.8 |
| 4 | Gemini 3.5 Flash | 49.9 |
| 5 | Qwen 3 VL 8B (Thinking) | 46.9 |
| 6 | InternVL3.5-8B | 45.8 |
Interactive version: theaggregate.ai/benchmark?slug=aha-memes · How It Works · Data refreshed daily, snapshot 2026-09-29.