Claude Fable 5.2 tops VIALS-AA with 1.60 tool calls per turn, most of any model
ArtificialAnlys · x · 2026-11-10
Artificial Analysis published per-turn tool-call stats for the VIALS-AA life-sciences visual reasoning benchmark: Claude Fable 5.2 (max) leads with 1.60 tool calls per turn, well ahead of Grok 4.7 at 1.31, while OpenAI models like GPT-6 Astra sit near the bottom at 1.0 — highlighting divergent vendor strategies on how aggressively models use tools.
More from Models
- Claude Fable 5.2 scores 64.9% on RoboDojo robot control, dominating rivals — burny_tech · 2026-11-10
- Claude Fable 5.2 video demo wows on pacing, but AI-sounding music persists — jiayuan_jy · 2026-11-10
- Gemini Notebooks keeps pulling context from old conversations, user reports — AnonymousDork929 · 2026-11-10
- User complains model takes four minutes to compare two 16-token completions — cephaloform · 2026-11-10
- DavidAU releases Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF merge — mp3m4k3r · 2026-11-10
- Uncensored Gemma 4 31B 'heretic' build hits Hugging Face, 11.9GB quantized — alexcovo_eth · 2026-11-10