BEACON
Thirteen native tasks; some reuse OpenVaccine, Optimus and CRISPR datasets.
13 benchmark-wide protocols · 221 benchmark-wide rows (not a task subtotal)D6 · Generation & design
Design or rank guides to minimize off-target activity.
Benchmark coverage
Thirteen native tasks; some reuse OpenVaccine, Optimus and CRISPR datasets.
13 benchmark-wide protocols · 221 benchmark-wide rows (not a task subtotal)Evaluation protocols
| Protocol | Track | Split / subset | Comparability |
|---|---|---|---|
PROT-B09-CRI-OFF-OFFICIAL-TRAIN-VALIDATION-T-99C679B7-569015B8 | CRI-Off B09-TR12 | official train/validation/test split CRI-Off | same_table_comparable external_data_policy;inference_budget |