HyperGVL - Vertex Counting: leaderboard
HyperGVL (2026) hypergraph task for vision-language models: counting the vertices of a hypergraph, with each of 200 problems posed in 35 textual and visual representations. Accuracy (%); higher is better.
Metric: Accuracy (%) on counting the vertices 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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 3 12B | 99.8 | #2059 |
| 2 | Gemini 3 Flash | 99.73 | #175 |
| 3 | Qwen 3 VL 8B | 99.6 | #917 |
| 4 | GPT-4o | 98.29 | #751 |
| 5 | Qwen 2.5 VL 7B Instruct | 95.41 | #1902 |
| 6 | GLM-4V-9B | 91.34 | #3142 |
| 7 | InternVL3-8B | 88.93 | #1782 |
| 8 | InternVL2.5-8B | 73.34 | #2370 |
| 9 | DeepSeek-VL2 | 48.59 | #2927 |
| 10 | Molmo-7B-D-0924 | 42.24 | #7207 |
| 11 | LLaVA-NeXT-7B | 19.56 | #5032 |
| 12 | LLaVA-v1.5-7B | 14.1 | #7630 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=hypergvl-vertex-counting · How It Works · Data refreshed daily, snapshot 2026-11-21.