Numbers with names, dates and limits.
Rangabot reports numerator and denominator, suite version, model, hardware context and execution errors. Targeted reruns never become complete-suite claims.
CapabilityResultEvidence scopeState
Core conversation candidate59/60
v1.0.11 · llama3.2:3b · complete run
ConditionalCritical trust cases22/22
One complete run; repetition still required
PassReasoning cases5/5
Same candidate and frozen rubric
PassMemory relevance precision15/15
Synthetic selection audit
PassMemory relevance recall15/15
Synthetic selection audit
PassTeacher answer quality50/60
Latest recorded public result
Below gateTeacher grounding54/60
90%; target is at least 95%
Below gateAnalytical transfer10/12
Frozen astronomy holdout
Below gateWhat this proves
A candidate, not a universal promise.
Model behavior varies by model, quantization, context, hardware and run. These results describe exact evaluated candidates. They do not imply that every Ollama model will match them.
Full model answers, personal chats, saved memories, document titles and Knowledge Vault files remain Git-ignored. Public methodology and aggregate results are reviewable.
Read the frozen contract ↗