Skip to main content
jzhao
Projects
intro-example
Evaluations
Log in
Sign up
Overview
Traces
Evals
Playground
Monitors
Leaders
Threads
Assets
Evaluations
Filter
inputs
output
fruit_name_score
MultiTaskBinaryClassificationF1
correct
color
Trace
Feedback
Status
model
self
true_count
true_fraction
f1
precision
recall
Evaluation.evaluate
b5d8
gpt4:v0
fruit_eval:v0
2
0.6667
1
1
1