HyperGVL - Reasoning: leaderboard
HyperGVL (2026) tests vision-language models on hypergraph reasoning: order-weighted shortest path and maximum flow, isomorphism, 3-coloring, strict hypercycles and Hamilton paths, each problem posed in 35 textual and visual representations. Average accuracy (%) over the six reasoning tasks; higher is better.
Metric: Average accuracy (%) over the six reasoning tasks (order-weighted shortest path and maximum flow, isomorphism, 3-coloring, strict hypercycle, Hamilton path), 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 February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 62.04 | #175 |
| 2 | GPT-4o | 35 | #751 |
| 3 | Qwen 3 VL 8B | 34.43 | #917 |
| 4 | Gemma 3 12B | 25.53 | #2059 |
| 5 | Qwen 2.5 VL 7B Instruct | 21.3 | #1902 |
| 6 | InternVL3-8B | 20.52 | #1782 |
| 7 | GLM-4V-9B | 18.9 | #3142 |
| 8 | InternVL2.5-8B | 16.35 | #2370 |
| 9 | Molmo-7B-D-0924 | 12.83 | #7207 |
| 10 | LLaVA-v1.5-7B | 12.28 | #7630 |
| 11 | LLaVA-NeXT-7B | 11.99 | #5032 |
| 12 | DeepSeek-VL2 | 8.21 | #2927 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=hypergvl-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.