Live Benchmarks

Godot Benchmark

Performance results of AI coding models on Godot tasks, measuring success rate and execution time with high precision.

View on GitHubTotal tasks: 15Last run: 7/20/2026

Model Performance

ModelPassedAvg DurationSuccess Rate
#1
gemini-3.1-proNEW
14215.6s
93%
#2
gemini-3.5-flash
12403.2s
80%
#3
claude-4-6-sonnet
9415.6s
60%
#4
deepseek-4-pro
5529.8s
33%
#5
glm-5.1
4438.1s
27%