Home › Evidence

deepseek-r1 scored 0.7817 (Competent) across 12 cognitive dimensions and 24 tasks

claim_id: alitheion-eval-deepseek-r1 · last verified never
JSON
deepseek-r1 scored 0.7817 (Competent) across 12 cognitive dimensions and 24 tasks · source: corpus_taas_profiles · total: ? · showing 0 rows · verified never

Per-dimension TAAS evidence for deepseek-r1. Source: corpus_taas_profiles (rolled-up audit results) with 24 task executions recorded in taas_execution_audits. Methodology: aletheion 12-dimension cognitive battery.

dimensionscoren_tasksn_passedn_failedagi_levelpercentiletask_scores
no rows matched the filter