Visual Extraction on Sandbox
1Success RateBloClaw
Evaluation Results
| Method | Links | |
|---|---|---|
| BloClawLLM Code Behavior=Uses plt.show()2026.04 | 1 | |
| BloClawLLM Code Behavior=Forgets to save figure2026.04 | 1 | |
| BloClawLLM Code Behavior=Uses plotly w/o HTML2026.04 | 0.984 | |
| Standard EvalLLM Code Behavior=Uses plt.show()2026.04 | 0 | |
| Standard EvalLLM Code Behavior=Forgets to save figure2026.04 | 0 | |
| Standard EvalLLM Code Behavior=Uses plotly w/o HTML2026.04 | 0 |