Identity correlation: linking accounts that belong to the same person
Claude models
Open-weights
View
Linkage F1 by difficulty tier — higher is better
Hover a bar for its value and interval; click a bar to spotlight that model (click again or press Esc to release).
n = 18 / 16 / 16 samples per model (easy / medium / hard; 50 pooled); the theoretical maximum is below 1 because some accounts never post, so even a perfect solver cannot link them. Where shown, Opus 4.5 and 4.6 used a fixed 12k-token thinking budget; all other models used adaptive thinking.