Compare companies

Side-by-side MCP results for companies evaluated by Codex. Compare score, rank, discoverability, cost, errors, runtime, and the underlying eval artifacts.

Model

Claude Code Codex

Codex

Tooling

API CLI MCP

Choose 2-4 companies

Selected

Company 1

Company 2

Selected

Company 1

Company 2

Prefect

Durable Workflow

fastCRW

Webscraping

Summary

Compare status

Comparable

Overall score

Best

Grade

Category

Durable Workflow

Webscraping

Overall rank

#37

#15

Best

Category rank

Best

Full eval

Open report

MCP Task Scoring

Task score

31%

89%

Best

Task

Failed+0The agent correctly used MCP tools for discovery and inspection (steps 1-2), properly identified that the Prefect MCP se...

Passed+30The agent successfully completed all required tasks: (1) discovered the available MCP tool (crw_scrape), (2) scraped htt...

Best

Used MCP Correctly

Passed+20Agent made 10 MCP tool calls

Best

Passed+20Agent made 1 MCP tool calls

Best

Partial Credit

Partial+5Partial credit: 50%

Passed+10Partial credit: 100%

Best

Zero Errors

Failed+0Tool outputs with errors: 7

Passed+10No errors

Best

Efficiency

Partial+1.022 tool calls (<=25, below average)

Passed+102 tool calls (<=5, excellent)

Best

Time

Partial+2.0189s (3-5min, slow)

Partial+3.5134s (2-3min, good)

Best

Cost

Partial+3.5$0.22 ($0.20-0.40, good)

Partial+6$0.11 ($0.10-0.20, great)

Best

Runtime (actual)

3m 8s

2m 13s

Best

Cost (actual)

$0.2242

$0.1112

Best

Tool calls

Best

Errors

Best

Tokens used

835,661

256,873

Best

MCP Discovery

Discovery score

89%

Best

55%

Official MCP

Passed5/5

Best

Passed5/5

Best

Auth Method

Passed15/15env var

Best

Passed15/15env var

Best

Tool Count

Passed10/1015 tools, lean

Best

Passed10/101 tools, lean

Best

Tool Description Length

Partial7/103,307 tokens, moderate

Passed10/106 tokens, lean

Best

llms.txt

Passed10/10

Best

Passed10/10

Best

Output Schema

Failed0/5

Best

Failed0/5

Best

Tool Stability

Passed5/5

Best

Passed5/5

Best

Security Posture

Partial9/10No API keys or credentials visible in tool definitions; all tools are read-only inspection operations with no destructiv...

—

Tool API Mapping

Partial14/15Tools map cleanly 1:1 to individual API read operations (get_flows, get_deployments, get_task_runs, etc.) with consisten...

—

Description Clarity

Partial14/15Descriptions are comprehensive and explicit about tool purpose, parameters, filter operators, and usage examples; only m...

—

Eval Details

Integration task

# Task Using the Prefect MCP, interact with the workflow engine: 1. Discover available MCP tools and their capabilities 2. List existing workflow executions (or deployments/flows...

# Task Using the fastCRW MCP, scrape web content: 1. Discover available MCP tools and their capabilities 2. Scrape the page at "https://news.ycombinator.com" 3. Extract the top 5...

Generated files

Trace tool calls

Completed

10/4/2026

9/27/2026

Stderr

None captured

Metric	Prefect Durable Workflow	fastCRW Webscraping
Summary
Compare status	Comparable	Comparable
Overall score	48	79 Best
Grade	D	B
Category	Durable Workflow	Webscraping
Overall rank	#37	#15 Best
Category rank	#1 Best	#1 Best
Full eval	Open report	Open report
MCP Task Scoring
Task score	31%	89% Best
Task	Failed+0The agent correctly used MCP tools for discovery and inspection (steps 1-2), properly identified that the Prefect MCP se...	Passed+30The agent successfully completed all required tasks: (1) discovered the available MCP tool (crw_scrape), (2) scraped htt... Best
Used MCP Correctly	Passed+20Agent made 10 MCP tool calls Best	Passed+20Agent made 1 MCP tool calls Best
Partial Credit	Partial+5Partial credit: 50%	Passed+10Partial credit: 100% Best
Zero Errors	Failed+0Tool outputs with errors: 7	Passed+10No errors Best
Efficiency	Partial+1.022 tool calls (<=25, below average)	Passed+102 tool calls (<=5, excellent) Best
Time	Partial+2.0189s (3-5min, slow)	Partial+3.5134s (2-3min, good) Best
Cost	Partial+3.5$0.22 ($0.20-0.40, good)	Partial+6$0.11 ($0.10-0.20, great) Best
Runtime (actual)	3m 8s	2m 13s Best
Cost (actual)	$0.2242	$0.1112 Best
Tool calls	22	2 Best
Errors	7	0 Best
Tokens used	835,661	256,873 Best
MCP Discovery
Discovery score	89% Best	55%
Official MCP	Passed5/5 Best	Passed5/5 Best
Auth Method	Passed15/15env var Best	Passed15/15env var Best
Tool Count	Passed10/1015 tools, lean Best	Passed10/101 tools, lean Best
Tool Description Length	Partial7/103,307 tokens, moderate	Passed10/106 tokens, lean Best
llms.txt	Passed10/10 Best	Passed10/10 Best
Output Schema	Failed0/5 Best	Failed0/5 Best
Tool Stability	Passed5/5 Best	Passed5/5 Best
Security Posture	Partial9/10No API keys or credentials visible in tool definitions; all tools are read-only inspection operations with no destructiv...	—
Tool API Mapping	Partial14/15Tools map cleanly 1:1 to individual API read operations (get_flows, get_deployments, get_task_runs, etc.) with consisten...	—
Description Clarity	Partial14/15Descriptions are comprehensive and explicit about tool purpose, parameters, filter operators, and usage examples; only m...	—
Eval Details
Integration task	# Task Using the Prefect MCP, interact with the workflow engine: 1. Discover available MCP tools and their capabilities 2. List existing workflow executions (or deployments/flows...	# Task Using the fastCRW MCP, scrape web content: 1. Discover available MCP tools and their capabilities 2. Scrape the page at "https://news.ycombinator.com" 3. Extract the top 5...
Generated files	1	1
Trace tool calls	22	2
Completed	10/4/2026	9/27/2026
Stderr	None captured	None captured