ArtifactBench - Attribute Ranking: leaderboard
Ranking models by their reported results on ArtifactBench (Yu et al., 2026), a graph of Hugging Face models, datasets and evaluation records: for each test dataset, the LLM orders the evaluated models by predicted score from their metadata alone. Kendall tau from -1 to 1 against the reported order; higher is better.
Metric: Kendall's tau (-1 to 1; per-dataset ranking of models by predicted score against the reported ranking, on model-dataset evaluation edges of a Hugging Face artifact graph (transductive test split), targets are the reported metric values normalized to 0-1; the LLM reads the model and dataset metadata without graph context). Source: arxiv.org. Saturation forecast: Around February 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 0.37 | #172 |
| 2 | Qwen 3 8B | 0.17 | #1838 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=artifactbench-attribute-ranking · How It Works · Data refreshed daily, snapshot 2026-11-12.