ATOM3D
A living collection of eight curated 3D molecular-learning tasks spanning small molecules, protein interactions and mutations, ligand binding, and protein/RNA structure ranking.
Scientific domain
Protein structure
Protein folding
蛋白质结构
15 registered benchmarks and tracks
BioMysteryBench
An agentic bioinformatics benchmark of objective, expert-authored mysteries over anonymized real-world biological data, scored on final answers rather than prescribed analysis paths.
CaM benchmark
A multistate protein sequence-design benchmark spanning CaM conformations and binding modes.
CAMEO
Weekly, automated, independent, blind evaluation of registered macromolecular structure-prediction servers on complete PDB entries whose experimental structures are withheld during prediction.
CASP
Biennial blind community experiments that assess macromolecular structure, complex, ligand, and model-accuracy prediction against experimental structures withheld during prediction.
CASP17 Immune Complexes
Dedicated CASP17 category for blind prediction of antibody-antigen, nanobody-antigen, and T-cell receptor complex structures.
CASP Protein-Ligand Prediction
Formal CASP track for blind prediction of protein-ligand binding poses, binding affinity or rank, binding pockets, and pose confidence.
CASP Protein Monomers
Formal CASP track assessing blind predictions of single-protein structures and post hoc protein evaluation units against withheld experimental coordinates.
CASP Protein Multimers
Formal CASP track assessing blind protein-complex predictions, including overall folds, interfaces, stoichiometry-free phases, and model-selection phases.
CompBioBench
A 100-task agent benchmark of objectively gradable computational-biology problems requiring multi-step reasoning, bespoke code, tools, and real-world external resources.
LifeSciBench
Expert-authored, artifact-rich free-response tasks that evaluate realistic research judgment across applied life-science workflows.
PapD benchmark
A multistate protein sequence-design benchmark targeting the multispecific PapD binding interface.
ProteinLMBench
A creator-curated set of 944 protein-science multiple-choice questions with answer explanations, generated from research literature and released for evaluating text LLM protein understanding.
RfaH benchmark
A multistate protein sequence-design benchmark using the fold-switching conformations of RfaH.
TAPE
A five-task benchmark for protein representation learning spanning secondary structure, residue contacts, remote homology, fluorescence, and stability.
Capability coverage
Registry records tagged Protein structure, counted by capability.
Accessible data table
| Capability | Records |
|---|---|
| Knowledge | 1 |
| Evidence synthesis | 1 |
| Retrieval | 2 |
| Prediction | 9 |
| Classification | 2 |
| Regression | 3 |
| Design | 4 |
| Generation | 1 |
| Optimization | 4 |
| Data analysis | 3 |
| Coding | 2 |
| Tool use | 2 |
| Experiment planning | 1 |
| Troubleshooting | 1 |
| Scientific reasoning | 4 |
| Scientific communication | 1 |
Scientific Tasks in this domain
Task mappings are evidence-backed and may be partial for mixed suites.
Coverage-gap reading: zero counts indicate a gap in this registry, not proof that no benchmark exists. Propose a primary source through the contribution form.