Performance results of AI coding models on Godot tasks, measuring success rate and execution time with high precision.
| Model | Passed | Avg Duration | Success Rate |
|---|---|---|---|
| #1 gemini-3.1-proNEW | 14 | 215.6s | 93% |
| #2 gemini-3.5-flash | 12 | 403.2s | 80% |
| #3 claude-4-6-sonnet | 9 | 415.6s | 60% |
| #4 deepseek-4-pro | 5 | 529.8s | 33% |
| #5 glm-5.1 | 4 | 438.1s | 27% |