Back to leaderboard
Compare companies
Side-by-side API results for companies evaluated by Codex. Compare score, rank, discoverability, cost, errors, runtime, and the underlying eval artifacts.
Model
Choose 2-4 companies
Selected
Selected
Prefect
Durable Workflow
fastCRW
Webscraping
Summary
Compare status
Comparable
Comparable
Overall score
73
84
BestGrade
C
B
Category
Durable Workflow
Webscraping
Overall rank
#50
#6
BestCategory rank
#2
#1
BestFull eval
Agent Performance
Eval score
74%
78%
BestTask success
Yes
Yes
Cost
$0.3187
$0.2137
BestTool calls
19
Best26
Errors
1
Best9
Runtime
1m 42s
59s
BestTokens used
500,718
Best780,562
Exit code
0
Best0
BestDiscoverability
Eval Details
Integration task
# Task
Using https://docs.prefect.io, complete the following task:
Using the Prefect Python SDK, build me a script that defines and executes a simple 3-step workflow:
1. Install...
# Task
Using https://docs.fastcrw.com/, complete the following task:
Using the fastCRW Python SDK, build me a script that scrapes web content:
1. Install the official fastCRW Py...
Generated files
1
1
Trace tool calls
19
26
Completed
9/29/2026
9/26/2026
Stderr
None captured
None captured