Vals Index: Anthropic still leads as GPT-6.2 Astra debuts at No. 7

lyraxana · x · 2026-11-18

After the GPT-6.2 release, the Vals Index (GDP-weighted agentic benchmarks) still favors Anthropic: Claude Fable 5.2 leads at 71.31%, with Sonnet 5.5 and Gemini 4 Carbon next. New entrants GPT-6.2 Astra (67.66%) and Sol (66.06%) land 7th and 9th, below Claude and Gemini leaders; Kimi K3.1 Pro, DeepSeek V4.1 Flash, GLM 5.3 and Qwen models also rank. Artificial Analysis at max effort: Astra 62.1, Sol 57.3, Fable 5.2 64.6.

Related event: Anthropic tops Vals Index as GPT-6.2 lands seventh(2 posts)→

Original post →

More from Models

Models channel →