Performance results of AI coding models on Typesense tasks, measuring success rate and execution time with high precision.
| Model | Passed | Avg Duration | Success Rate |
|---|---|---|---|
| #1 gemini-3.5-flashNEW | 15 | 338.3s | 100% |
| #2 claude-4-6-sonnet | 14 | 244.9s | 93% |
| #3 MiniMax-M3 | 14 | 343.2s | 93% |
| #4 claude-5-sonnet | 7 | 728.7s | 78% |
| #5 glm-5.2 | 11 | 523.9s | 73% |
| #6 deepseek-4-pro | 6 | 681.3s | 67% |
| #7 gemini-3.5-flash | 19 | 754.0s | 53% |