Performance results of AI coding models on Prembly tasks, measuring success rate and execution time with high precision.
| Model | Passed | Avg Duration | Success Rate |
|---|---|---|---|
| #1 gemini-3-flashNEW | 8 | 294.8s | 67% |
| #2 glm-4.7 | 7 | 473.2s | 58% |
| #3 gemini-3.1-pro | 7 | 291.4s | 58% |
| #4 claude-4-6-sonnet | 6 | 326.7s | 50% |