Fable 5.2's Edge Over Opus 5.5 Grows With Task Length: 93% vs 85% at 16+ Turns
arena · x · 2026-11-14
Agent Arena data shows Fable 5.2's advantage over Opus 5.5 widens with conversation length, measured by % of responses needing no user correction:
- Up to 3 replies: roughly level, 85% correction-free
- 4–7 replies: 86% vs 81%
- 8–15 replies: 89% vs 83%
- 16+ replies: 93% vs 85%
Takeaway: on everyday short tasks you won't notice much difference — the gap shows up on difficult, long-running work.
More from Models
- AssemblyAI Adds GPT-6.1 Terra, Beam-1, DeepSeek V4.1 Flash to LLM Gateway — AssemblyAI · 2026-11-14
- Continual Learning Won't Block Full Research Automation — but Will Block Enterprise Adoption — ChrisGPT · 2026-11-14
- Arena weekly: Claude Fable 5.2 tops Agent Arena, Gemini 4 Hydrogen fastest — arena · 2026-11-14
- Open models trail frontier by six months, but that matters less than you think — latkins · 2026-11-14
- Japan's ai& launches Kimi K3.1 Pro and Meta's Muse Spark Open with day-0 pricing — DavidBennett__ · 2026-11-14
- Alan Thompson memo: 18 models in 13 days, Gemini 4 elements, RLI heading to 98% — dralandthompson · 2026-11-14