| Benchmark | Model | Rank | Results |
|---|---|---|---|
| agents-on-agents-last-exam-ale-cli | Step 5 Preview (High) | – | Pass Rate: 29.5 |
| code-generation-on-deepswe | Step 5 Preview (High) (SWE-agent) | – | Pass@1: 0.677 |
| code-generation-on-programbench | Step 5 Preview (High) | – | Average Test Pass Rate: 80.5 |
| code-generation-on-terminal-bench-4-0 | Step 5 Preview (High) | – | Accuracy: 33.3 |