Single-Repo task execution on A2A-Agentization Bench (Hard)
14.2Execution Success RateCodex
Evaluation Results
| Method | Links | |
|---|---|---|
| Codex2026.04 | 14.2 | |
| Claude Code2026.04 | 10.4 | |
| OpenHands2026.04 | 10.4 | |
| EnvX2026.04 | 10.4 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Codex2026.04 | 14.2 | |
| Claude Code2026.04 | 10.4 | |
| OpenHands2026.04 | 10.4 | |
| EnvX2026.04 | 10.4 |