MazeBench Update: Fable 5.2 Matches GPT-6 Astra at Half the Price

Fable 5.2 scored 15% on MazeBench, nearly matching GPT-6 Astra at half the price and earning the title of most token-efficient model; Gemini 4 Carbon matched its predecessor's score but was criticized for scattered, distractible strategies.

2026-11-11 ~ 2026-11-11 · 3 related posts

• MazeBench: Fable 5.2 scores 15%, near-frontier at half price; Gemini 4 Carbon 11% — patience_cave · 2026-11-11
• Fable 5.2 takes MazeBench frontier, matches GPT-6 Astra puzzle-solving — patience_cave · 2026-11-11
• Gemini 4 Carbon matches predecessor's score but explores less, gets distracted — patience_cave · 2026-11-11