Fable 5.2 cuts refusals dramatically but slides to 40th & 53rd on BullshitBench
burny_tech · x · 2026-11-12
petergostev shares Claude Fable 5.2's BullshitBench results: refusals are way down — Fable 5 declined 1/3 of prompts, 5.2 nearly none — but performance dropped notably, ranking 40th (Max reasoning, 67.3% clear) and 53rd (Low, 63.3%), where Fable/Opus previously dominated the Top 10, suggesting a trade-off between fewer refusals and bullshit detection.
More from Models
- KOL predicts Gemini will be the top frontier LLM by year-end as rivals stumble — iruletheworldmo · 2026-11-12
- Dense rewards lose to standard GRPO at matched compute, arXiv paper finds — burny_tech · 2026-11-12
- Dev builds npx driftcost CLI to check if Claude Code token usage silently shifted between Opus versions — Tough_Stay8909 · 2026-11-12
- Reflection's Beam free until Nov 12; fx is a 5.97MiB Zig-native open coding agent — evilrabbit_ · 2026-11-12
- Community speculates Google may announce Gemini 4 (Krypton) instead of Gemini 4 Flash — algo_diver · 2026-11-12
- Artificial Analysis: Upgrading Claude model tier beats maxing reasoning effort on cost — ArtificialAnlys · 2026-11-12