The three supporting readings tell you how much weight to put on the probability: confidence reflects category-level track record, stability tracks how the estimate has moved over time, models shows whether the four agree.
Belief trajectory
Loading belief trajectory...
Per-model probabilities
GPT-4o
30%-12 vs avg
Gemini
75%+33 vs avg
Claude
28%-14 vs avg
Grok
35%-7 vs avg
Key disagreementGemini (75%) vs Claude (28%): Different weighting of factors