@allen_ai: Most models are only evaluated on a fraction of the benchmarks out there. ArtifactLinker, our new system, predicts whic…

X AI KOLs Following Tools

Summary

Allen AI introduces ArtifactLinker, a system that predicts which AI models will achieve state-of-the-art results on HuggingFace benchmarks and then verifies by running evaluations.

Most models are only evaluated on a fraction of the benchmarks out there. ArtifactLinker, our new system, predicts which ones would set a new state-of-the-art on benchmarks hosted on @HuggingFace, then runs the evaluation to verify. 🧵 https://t.co/DXk3FbndMF
Original Article
View Cached Full Text

Cached at: 05/23/26, 12:03 PM

Most models are only evaluated on a fraction of the benchmarks out there.

ArtifactLinker, our new system, predicts which ones would set a new state-of-the-art on benchmarks hosted on @HuggingFace, then runs the evaluation to verify.

ArtifactLinker is built on a graph of HuggingFace data—models & datasets are nodes, and reported eval scores form the edges.

We trained a GNN for it to rank which models are likely to reach a new SOTA on which benchmarks, beating prompting-based LLMs.

In ArtifactLinker, an LLM coding agent writes and runs the evaluation code, with shared memory across runs.

We found that it comes within 80% of the officially reported score 72.6% of the time.

Using ArtifactLinker, we found cases where a strong model had never been evaluated on a benchmark it would set – or near-match – the SOTA on.

We also found that newer LLMs like Gemma often lose to older DeBERTa models on natural language inference tasks.

We’re releasing a dataset of 14K HuggingFace models, datasets, papers, & codebases linked by 51K evaluations, fine-tunings, & references, plus the ArtifactLinker code.

We hope it helps others find SOTA eval results.

Code: https://github.com/allenai/artifact-linker… Data: https://huggingface.co/datasets/lwaekfjlk/artifact-bench…

Similar Articles