# Best AI model for coding › agentic — October 2026

As of Oct 14, 2026, Claude Opus 5.5 & Claude Sonnet 5.5 are tied for state of the art in Coding › Agentic (since Oct 6, 2026; sources Terminal-Bench 4.0; methodology v1.0).

Category board: https://isitsota.com/c/coding-agentic

## Top 10

- #1 Claude Opus 5.5
- #1 Claude Sonnet 5.5
- #2 GPT-6.1 Sol
- #2 GPT-6 Astra
- #3 Claude Fable 5.1
- #4 Claude Opus 5
- #5 GPT-6 Sol
- #6 Claude Fable 5
- #7 GLM 5.3
- #8 Grok 4.7

## Crown changes

- Oct 6, 2026 — Coding › Agentic: Claude Opus 5.5 and Claude Sonnet 5.5 are co-SOTA

## Weights

- Terminal-Bench 4.0: primary, weight 1
- Terminal-Bench 2.0: display, weight 0