HyperGVL - Hyperedge Counting: leaderboard
HyperGVL (2026) hypergraph task for vision-language models: counting the hyperedges of a hypergraph, with each of 200 problems posed in 35 textual and visual representations. Accuracy (%); higher is better.
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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 98.31 | #180 |
| 2 | GPT-4o | 80.29 | #754 |
| 3 | Qwen 3 VL 8B | 59.41 | #927 |
| 4 | Gemma 3 12B | 57.91 | #2091 |
| 5 | InternVL3-8B | 47.93 | #1795 |
| 6 | Qwen 2.5 VL 7B Instruct | 41.94 | #1919 |
| 7 | GLM-4V-9B | 39.37 | #3164 |
| 8 | InternVL2.5-8B | 22.93 | #2393 |
| 9 | Molmo-7B-D-0924 | 17.94 | #7206 |
| 10 | DeepSeek-VL2 | 17.73 | #3056 |
| 11 | LLaVA-NeXT-7B | 11.17 | #5045 |
| 12 | LLaVA-v1.5-7B | 8.63 | #7642 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=hypergvl-hyperedge-counting · How It Works · Data refreshed daily, snapshot 2026-11-22.