ArtifactBench - Attribute Ranking: leaderboard

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 July 2027. 2 models tracked.

Top models

#ModelScore
1GPT-5.20.37
2Qwen 3 8B0.17

Interactive version: theaggregate.ai/benchmark?slug=artifactbench-attribute-ranking · How It Works · Data refreshed daily, snapshot 2026-09-26.