Paste per-model answers plus the truth label. Get the effective independent vote count n_eff. No upload, no server — this runs entirely in your browser.
n_eff = N / (1 + (N−1)·r̄), where r̄ is the mean pairwise correlation of each model's error indicators (wrong = 1). It estimates how many independent voters a panel behaves like. If every model failed on the same items, r̄ → 1 and n_eff → 1 no matter how many models you added. It is not the panel's accuracy; it is how much independent evidence the panel carries.
The trap: adding weak, near-random models can raise n_eff, because random mistakes don't agree. Report n_eff for a competent panel (drop models near chance), or n_eff will flatter the headcount.
On HELM openbookqa (multiple_choice_joint, 500 items), 31 models from 11+ families:
r̄ = 0.251, n_eff = 3.63 of 31. Restricting to models with accuracy ≥ 0.40 (26 models):
r̄ = 0.353, n_eff = 2.64 of 26. One best model per family (11): n_eff = 2.95 of 11.
Same regime as the published literature (Nine Judges ≈ 2 of 9; Wavering Oracles 2.58 of 7).