AkitaOnRails LLM benchmark v4 covers Gemini 4 Argon and GPT-6.1 Sol

AkitaOnRails says their benchmark agrees with another result; their LLM benchmark v4 compares Gemini 4 Argon, GPT-6.1 Sol, Kimi K3.1 Pro and Claude Sonnet 5.5.

Fabio Makita

@AkitaOnRailsArchived 12 hours agoOriginally posted 2026.10.28

AkitaOnRails LLM benchmark v4 covers Gemini 4 Argon and GPT-6.1 Sol

Fabio Makita @AkitaOnRailsOriginally posted 2026.10.28

Open original on X

Consistent with my own benchmark: https://akitaonrails.com/en/2026/10/28/llm-benchmark-v4-gemini-4-argon-gpt-6-1-sol-terra-kimi-k3-1-pro-claude-sonnet-5-5/

This post quotes another post: x.com/miaai_lab/status/2115353694019432648

x.com/akitaonrails/status/2115442425816551513Archived 2026.10.29 10:02

Open original on X