Automated Data Science on hurricane BLADE
8.8BLADE Average ScoreAGENTIC-IMODELS
Evaluation Results
| Method | Links | |
|---|---|---|
| AGENTIC-IMODELSAgent=Codex CLI2026.05 | 8.8 | |
| AGENTIC-IMODELSAgent=Claude Code2026.05 | 8.7 | |
| StdAgent=Codex CLI2026.05 | 8.7 | |
| AGENTIC-IMODELSAgent=Copilot (Gemini)2026.05 | 8.6 | |
| AGENTIC-IMODELSAgent=Copilot (Sonnet)2026.05 | 8.5 | |
| StdAgent=Claude Code2026.05 | 7.3 | |
| StdAgent=Copilot (Sonnet)2026.05 | 5.8 | |
| StdAgent=Copilot (Gemini)2026.05 | 5.1 |