Loading views...

Agent Graph Eval Dataset

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Jun 10 18:5
Editor
Edited
Edited
2025 Jul 2 14:18
Refs
Refs
  • azure_model_20250610_183601_fa72b8a1: 7 observations, 11.516s, $0.009784
  • game_builder_crew_20250610_183601_3c1558c5: 17 observations, 60.419s, $0.122588
  • job_posting_20250610_183601_b937225b: 61 observations, 79.637s, $0.204064799996
  • lead_score_flow_20250610_183601_d4e22735: 363 observations, 26.935s, $0.380743999984
  • markdown_validator_20250610_183601_fea83374: 10 observations, 5.003s, $0.015692
  • marketing_strategy_20250610_183601_b347b44c: 43 observations, 161.096s, $0.233987999994
  • match_profile_to_positions_20250610_183601_638ace73: 18 observations, 6.455s, $0.012712
  • recruitment_20250610_183601_cf408109: 31 observations, 80.266s, $0.115108
  • screenplay_writer_20250610_183601_f2704435: 29 observations, 31.269s, $0.061095999998
  • starter_template_20250610_183601_effc9f38: 12 observations, 5.917s, $0.001539
Example
Observations
Duration
Cost
lead_score_flow
363
26.9s
$0.38
marketing_strategy
43
161.1s
$0.23
job_posting
61
79.6s
$0.20
game_builder_crew
17
60.4s
$0.12
recruitment
31
80.3s
$0.12
screenplay_writer
29
31.3s
$0.06
match_profile_to_positions
18
6.5s
$0.01
markdown_validator
10
5.0s
$0.02
azure_model
7
11.5s
$0.01
starter_template
12
5.9s
$0.00
  • lead_score_flow: 1.5MB (most complex workflow)
  • job_posting: 568KB
  • marketing_strategy: 566KB
  • Small ones: 25KB~191KB
 
 
 
 
 
 
 

Recommendations