Cost-Aware Evaluation Dashboard
Loading...
tau2
Charts
Trace Viewer
Selected
--
Avg Pass@1 Change
--
Avg Cost Savings
--
Models Improved
--
Performance vs Cost (Native + Cost-Aware)
Y:
Pass@1
Pass@4
Success Rate
Cache Hit Rate
Avg Turns
Avg Total Tokens
Avg Input Tokens
Avg Output Tokens
Tokens/Success
Cost/Success
Avg Latency
X:
Avg Cost ($)
Total Cost ($)
Avg Total Tokens
Avg Input Tokens
Avg Output Tokens
Avg Turns
Cost/Success ($)
Tokens/Success
Cache Hit Rate
Avg Latency
Domain:
All
Airline
Retail
Labels
Model Comparison
Metric:
Pass@1
Pass@4
Success Rate
Avg Cost ($)
Total Cost ($)
Avg Total Tokens
Avg Input Tokens
Avg Output Tokens
Avg Turns
Cache Hit Rate
Cost/Success ($)
Tokens/Success
Avg Latency
Domain:
All
Airline
Retail
Trace Viewer
Model:
— Select —
Mode:
Native
Cost-Aware
Domain:
Airline
Retail
Reward:
All
Success
Failure
Select a model to view traces