# Best AI model per dollar for coding — October 2026

As of Oct 14, 2026, Claude Opus 5.5 & Claude Sonnet 5.5 & GLM 5.3 & GLM 5.3 Flash & GPT-6 Luna are tied for state of the art in Coding, best per dollar (tracked since Oct 14, 2026; sources Terminal-Bench 4.0; methodology v1.0).

Category board: https://isitsota.com/c/coding?slice=pareto

## Top 10

- #1 Claude Opus 5.5
- #1 Claude Sonnet 5.5
- #1 GLM 5.3
- #1 GLM 5.3 Flash
- #1 GPT-6 Luna
- #2 GPT-6.1 Sol
- #2 GPT-6 Astra
- #3 Claude Fable 5.1
- #4 Claude Opus 5
- #5 GPT-6 Sol

## Crown changes


## Weights

- Terminal-Bench 4.0: primary, weight 1
- SWE-bench Pro V2 HARD: primary, weight 1
- LMArena Text (style-controlled, coding): primary, weight 0.6
- Terminal-Bench 2.0: secondary, weight 0.35
- Aider Polyglot: secondary, weight 0.35
- SWE-bench Verified: display, weight 0