HyperGVL - Isomorphism Recognition: leaderboard
Metric: Accuracy (%) on deciding whether two hypergraphs are isomorphic (yes/no), 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 July 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 64.6 |
| 2 | Qwen 2.5 VL 7B Instruct | 59.23 |
| 3 | GPT-4o | 59.14 |
| 4 | Gemma 3 12B | 51.29 |
| 5 | InternVL3-8B | 50.54 |
Interactive version: theaggregate.ai/benchmark?slug=hypergvl-isomorphism-recognition · How It Works · Data refreshed daily, snapshot 2026-10-07.