SemiAnalysis Launches GDPx Benchmark; Fable 5.2 Tops at 16.4%

SemiAnalysis launched the GDPx leaderboard, scoring models across 11 equally weighted domains on real economic tasks, with Claude Fable 5.2 debuting at the top with 16.4%. The benchmark also suggests Fable 5.2's recursive self-improvement (RSI) capability was deliberately flattened to Sonnet 5.5's level, scoring 24.1% in that domain.

2026-11-10 ~ 2026-11-10 · 2 related posts

• SemiAnalysis Launches GDPx Leaderboard: Claude Fable 5.2 Debuts on Top at 16.4% — scaling01 · 2026-11-10
• GDPx leaderboard shows Fable 5.2's RSI plateauing at Sonnet 5.5 level, matching Anthropic's training caps — morgymcg · 2026-11-10