All Competitors

A holistic evaluation framework for protein foundation models, assessing 25+ models across 8 tasks using four-dimensional metrics: quality, novelty, diversity, and robustness.

Comprehensive NeurIPS 2023 benchmark for protein inverse folding, evaluating 8 models across single-chain, multi-chain, and de novo design tasks.

Benchmark suite of five biologically relevant tasks for evaluating protein sequence representation learning, covering structure, homology, and engineering.