22 lines
625 B
JSON

{
"T_cat": 1.764438052305923,
"T_spec": 2.4588486682973603,
"per_benchmark": {
"GPT-5.4": {
"ece_cat_pre": 0.05087702547510463,
"ece_cat_post": 0.03403335139155388,
"ece_spec_pre": 0.06921947295467064,
"ece_spec_post": 0.041827132950226435,
"cat_preds_preserved": true,
"spec_preds_preserved": false
},
"Opus-4.6": {
"ece_cat_pre": 0.06293055539329852,
"ece_cat_post": 0.04372739652792611,
"ece_spec_pre": 0.08450941021243728,
"ece_spec_post": 0.05213142380118366,
"cat_preds_preserved": true,
"spec_preds_preserved": false
}
}
}