Public KG record
Ensemble (LLM arbiter)
Recorded overview
Ensemble of GPT-5, Gemini 3.1 Pro, Claude Opus 4.8 with LLM arbiter; accuracy 69
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Performance: Offline accuracy 69.35% on sibling node pairs
Evidence coverage
The KG currently records 6 known information dimensions and has 12 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Ensemble (majority vote) — related to
- Gemini 3.1 Pro — uses
- GPT-5 — uses
- Ensemble (majority vote) — related to