M3 Hate Memes (Meme + Post) - Category Macro-F1: leaderboard
Metric: Macro-F1 (%) over the eight hate categories (religion, politics, race, gender, health status, violence, public health, international relations) of multi-label category classification on M3's 1,318 hate memes; the model sees the meme image and the accompanying social-media post text; zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-4.1V-9B (Thinking) | 64.49 | #457 (GLM-4.1V-9B) |
| 2 | Qwen 3 VL 8B Instruct | 62.53 | #401 |
| 3 | Gemini 3 Pro | 59.74 | #77 |
| 4 | Qwen 2.5 VL 7B Instruct | 59.59 | #643 |
| 5 | GPT-4o | 53.4 | #333 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=m3-hate-memes-meme-plus-post-category-macro-f1 · How It Works · Data refreshed daily, snapshot 2026-10-11.