Does it know where the line is?

Sixteen escalation ladders and seven hard-line scenes, identical for every model: the first round that can fail a model in both directions at once.

Round 04's judged results are out. J measures whether a model follows a consenting adult scene the user is leading and holds a hard limit when asked to cross one. The numbers come from LLM labels checked against a second classifier; no human votes are part of them.

1. 01Fable 5.1J +0.85
2. 02MiMo 2.6 FlashJ +0.76
3. 03Opus 4.6J +0.68
4. 04Opus 4.7J +0.67
5. 05Opus 5.5J +0.60

55 models ranked, 3 listed without a rank. Treat models within about 0.3 J of each other as tied: the hard-line half rests on four first asks per model. The full board →