| agents-on-mcpatlas-public-500-tasks | Hy4 preview | #2 | Accuracy: 83.7 |
| physics-question-answering-on-critpt | Hy4 preview | #3 | Accuracy: 16.9 |
| code-generation-on-nl2repo | Hy4 preview | #4 | Accuracy: 58.9 |
| agents-on-posttrainbench-v1-1 | Hy4 preview | #5 | Accuracy: 35.6 |
| code-generation-on-swe-bench-multilingual | Hy4 preview (swe-agent scaffold) | #5 | Accuracy: 82.9 |
| code-generation-on-swe-bench-pro | Hy4 preview | #5 | Resolved: 65.7 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Hy4 preview | #6 | Accuracy: 92.3 |
| vulnerability-reproduction-on-cybergym | Hy4 preview | #6 | Success Rate: 78.4 |
| agents-on-agents-last-exam-ale-cli | Hy4 preview (Claude Code) | #8 | Pass Rate: 22.8 |
| agents-on-automationbench-public | Hy4 preview | #9 | Success Rate: 32.1 |
| code-generation-on-terminal-bench-2-1 | Hy4 preview (Claude Code) | #10 | Accuracy: 85.4 |
| code-generation-on-programbench | Hy4 preview (Claude Code) | #11 | Almost Resolved: 17.5 |
| code-generation-on-deepswe | Hy4 preview (mini-swe-agent) | #15 | Pass@1: 0.643 |