HyperGVL - Hyperedge Counting: leaderboard

Metric: Accuracy (%) on counting the hyperedges of a hypergraph, 7,000 questions per task (200 problems on synthetic and real-world hypergraphs, each posed in 35 textual, visual and combined hypergraph representations), accuracy (%) averaged over the representations, temperature 0.8, top-p 0.95; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.

Top models

#ModelScore
1Gemini 3 Flash98.31
2GPT-4o80.29
3Gemma 3 12B57.91
4InternVL3-8B47.93
5Qwen 2.5 VL 7B Instruct41.94

Interactive version: theaggregate.ai/benchmark?slug=hypergvl-hyperedge-counting · How It Works · Data refreshed daily, snapshot 2026-10-07.