CFMS - Sarcasm Identification: leaderboard

CFMS (Chinese Fine-grained Multimodal Sarcasm, 2026) collects Chinese social-media image-text posts annotated for sarcasm, its target and an explanation; models answer zero-shot. This board scores whether each post of the 420-post test split is sarcastic. Accuracy in percent; higher is better.

Metric: Accuracy (%) at deciding whether an image-text post is sarcastic, on the 420-item test split (about 45 percent sarcastic), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Flash71.19#463
2Qwen 2.5 VL 7B Instruct70.71#1902
3GPT-4o70.24#751
4InternVL2.5-8B68.48#2370

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cfms-sarcasm-identification · How It Works · Data refreshed daily, snapshot 2026-11-21.