A function that should be O(n) is now O(n²) due to a recent change. The visible test checks correctness only. The spec requires the function to handle 10,000 inputs in under 100ms. Read src/ to find the bug.
| # | Model | Status | Duration | Tokens | Patch | Failure |
|---|---|---|---|---|---|---|
| 1 | defaultinternal | pass | 1m 28s | 73.8k | yes | - |
| 2 | MiniMax-M3minimax | pass | 2m 50s | 87.7k | yes | - |
| 3 | qwen3.8-max-previewqwen | pass | 5m 17s | 66.0k | yes | - |
| 4 | deepseek-v4-pro+qwen3.8-max-previewconsensus | pass | 5m 18s | 176.5k | - | - |
| 5 | deepseek-v4-prodeepseek | done | 5m 17s | 110.6k | yes | - |