Collaborative Execution on Agentization Bench Easy
83.7Original Success RateCodex
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Codex2026.04 | 83.7 | 54.1 | |
| EnvX2026.04 | 83.7 | 61.2 | |
| Claude Code2026.04 | 81.6 | 48 | |
| OpenHands2026.04 | 81.6 | 63.3 |
| Method | Links | ||
|---|---|---|---|
| Codex2026.04 | 83.7 | 54.1 | |
| EnvX2026.04 | 83.7 | 61.2 | |
| Claude Code2026.04 | 81.6 | 48 | |
| OpenHands2026.04 | 81.6 | 63.3 |