HyperGVL - Strict Hypercycle: leaderboard

Metric: Accuracy (%) on finding a strict hypercycle, adjacent hyperedges sharing exactly one vertex, 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: Around January 2027. 12 models tracked.

Top models

#ModelScore
1Gemini 3 Flash66.44
2GPT-4o25.14
3Gemma 3 12B13.39
4Qwen 2.5 VL 7B Instruct10.51
5InternVL3-8B5.24

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