News for hackers. Stuff that matters.
Re:November 2026 Claude Fable 5.2 Scores 65 on Artificial An... by onlyrealcuzzo on Monday November 09, 2026 @04:44PM (#50432687)
If you compare Fable 5.2 Medium to Opus 5.5 high (settings that make sense - max is universally considered rarely worth it), you will see that Fable 5.2 is SUPPOSEDLY very cost competitive: https://artificialanalysis.ai/models/claude-fable-5-2?models...
Re:November 2026 Claude Fable 5.2 Scores 65 on Artificial An... by singularity2001 on Monday November 09, 2026 @05:50PM (#50433437)

  very cost competitive
Seeing the charts, I come to completely different conclusions.
Re:November 2026 Claude Fable 5.2 Scores 65 on Artificial An... by onlyrealcuzzo on Monday November 09, 2026 @05:59PM (#50433553)
The charts only show the cost per task - not whether or not they got the task correct - which makes flash models look way better than they actually are.