Evaluations
Filter
inputs
output
eval_multi_choice_confidence
eval_multi_choice
Trace
Feedback
Status
model
self
mean
true_count
1-50 of 8757
Per page:
50
Charts
3
Score summary
3
General
Cost
$0.01
↗+ $0.00
Tokens
19.4K
↗+ 11.95K
Latency
10.64s
↗+ 6.02s
eval_multi_choice
true_count
0
↘- 1
true_fraction
0
↘- 0.1
model_latency
mean
6.86
↗+ 2.43
eval_multi_choice_confidence
mean
-0.65
↗+ 0.2