Skip to main content

Changma's workspace

summary
4
summary/agent_abilities
summary/avg_metrics_comparison
Gpt-4Current RunLemur-70b00.20.40.6
Progress Rate (%)Success Rate (%)Average Metrics for All Tasks Compared to Baseline Models
Average Game Progress Rate
0.1589
Average Game Success Rate
0.025
Metric Name
Metric Value (%)
3
4
summary/all_results
List<File<(table)>>