GABench - Graph ML - Node Classification (Numerical-Attribute Graphs): leaderboard
Metric: Task success rate (%; share of tasks whose final answer a DeepSeek-V4-Flash judge marks consistent with the verified ground truth; node classification graph machine learning (node classification, link prediction, graph classification) with its 10 learning tools, which validate the configuration and return a fixed model accuracy rather than train on numerical-attribute graphs (DGraph-Fin, Pokec, NBA, Credit and Bail, 200 generated tasks per dataset and category); LLM agent in the OpenClaw harness, one run). Source: arxiv.org. Saturation forecast: Around 2032. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 32.54 |
| 2 | Qwen 3 235B A22B | 27.7 |
| 3 | Gemini 3 Flash | 26.66 |
| 4 | GLM-5-Turbo | 26.66 |
| 5 | DeepSeek V4 Pro | 20.88 |
| 6 | GLM-4.5 Flash | 8.57 |
Interactive version: theaggregate.ai/benchmark?slug=gabench-graph-ml-node-classification-numerical-attribute-graphs · How It Works · Data refreshed daily, snapshot 2026-09-29.