Compare companies

Side-by-side MCP results for companies evaluated by Claude Code. 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

Daytona

Sandboxes

Stripe

Payment

Summary

Compare status

Comparable

Overall score

Best

Grade

Category

Sandboxes

Payment

Overall rank

#39

#15

Best

Category rank

Best

Full eval

Open report

MCP Task Scoring

Task score

30%

83%

Best

Task

Failed+0The agent correctly used MCP tools for sandbox operations and successfully created a new sandbox (step 3). However, it f...

Passed+30The agent successfully completed all required tasks using only MCP tools. It: (1) discovered available MCP tools and the...

Best

Used MCP Correctly

Passed+20Agent made 16 MCP tool calls

Best

Passed+20Agent made 10 MCP tool calls

Best

Partial Credit

Partial+6Partial credit: 60%

Passed+10Partial credit: 100%

Best

Zero Errors

Failed+0Failed tool calls: 6

Passed+10No errors

Best

Efficiency

Failed+027 tool calls (>25, inefficient)

Partial+3.512 tool calls (<=15, good)

Best

Time

Partial+1.0329s (5-10min, very slow)

Partial+3.5137s (2-3min, good)

Best

Cost

Partial+3.5$0.37 ($0.20-0.40, good)

Partial+6$0.17 ($0.10-0.20, great)

Best

Runtime (actual)

5m 28s

2m 17s

Best

Cost (actual)

$0.3691

$0.1663

Best

Tool calls

Best

Errors

Best

Tokens used

873,418

300,154

Best

MCP Discovery

Discovery score

87%

Best

86%

Official MCP

Passed5/5

Best

Passed5/5

Best

Auth Method

Passed15/15env var

Best

Passed15/15env var

Best

Tool Count

Passed10/1012 tools, lean

Best

Passed10/109 tools, lean

Best

Tool Description Length

Partial7/102,341 tokens, moderate

Best

Partial7/103,797 tokens, moderate

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

Partial8/10No API keys or tokens visible in descriptions or schemas; parameters are clearly typed and input validation is present (...

Partial9/10No API keys or tokens visible in descriptions or schemas; parameters are well-typed with enums where appropriate; stripe...

Best

Tool API Mapping

Partial14/15Tools map cleanly 1:1 to individual sandbox operations (create, destroy, execute, file operations, git operations, previ...

Best

Partial12/15Most tools map 1:1 to API operations (stripe_api_search, stripe_api_read, stripe_api_write, stripe_api_details), but str...

Description Clarity

Partial13/15Tool descriptions are clear and specific about their purpose; most explain what they do and expected inputs/outputs, tho...

Best

Partial13/15Tool descriptions are generally clear with explicit guidance on when to use each tool (e.g., stripe_implementation_plann...

Best

Eval Details

Integration task

# Task Using the Daytona MCP, manage cloud sandboxes: 1. Discover available MCP tools and their capabilities 2. List all existing sandboxes (or environments/workers/deployments)...

# Task Using the Stripe MCP, create payment resources: 1. Discover available MCP tools and their capabilities 2. Create a product called "Pro Plan" using the MCP tools 3. Create...

Generated files

Trace tool calls

Completed

9/27/2026

Stderr

None captured

Metric	Daytona Sandboxes	Stripe Payment
Summary
Compare status	Comparable	Comparable
Overall score	47	83 Best
Grade	D	B
Category	Sandboxes	Payment
Overall rank	#39	#15 Best
Category rank	#2 Best	#2 Best
Full eval	Open report	Open report
MCP Task Scoring
Task score	30%	83% Best
Task	Failed+0The agent correctly used MCP tools for sandbox operations and successfully created a new sandbox (step 3). However, it f...	Passed+30The agent successfully completed all required tasks using only MCP tools. It: (1) discovered available MCP tools and the... Best
Used MCP Correctly	Passed+20Agent made 16 MCP tool calls Best	Passed+20Agent made 10 MCP tool calls Best
Partial Credit	Partial+6Partial credit: 60%	Passed+10Partial credit: 100% Best
Zero Errors	Failed+0Failed tool calls: 6	Passed+10No errors Best
Efficiency	Failed+027 tool calls (>25, inefficient)	Partial+3.512 tool calls (<=15, good) Best
Time	Partial+1.0329s (5-10min, very slow)	Partial+3.5137s (2-3min, good) Best
Cost	Partial+3.5$0.37 ($0.20-0.40, good)	Partial+6$0.17 ($0.10-0.20, great) Best
Runtime (actual)	5m 28s	2m 17s Best
Cost (actual)	$0.3691	$0.1663 Best
Tool calls	27	12 Best
Errors	6	0 Best
Tokens used	873,418	300,154 Best
MCP Discovery
Discovery score	87% Best	86%
Official MCP	Passed5/5 Best	Passed5/5 Best
Auth Method	Passed15/15env var Best	Passed15/15env var Best
Tool Count	Passed10/1012 tools, lean Best	Passed10/109 tools, lean Best
Tool Description Length	Partial7/102,341 tokens, moderate Best	Partial7/103,797 tokens, moderate 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	Partial8/10No API keys or tokens visible in descriptions or schemas; parameters are clearly typed and input validation is present (...	Partial9/10No API keys or tokens visible in descriptions or schemas; parameters are well-typed with enums where appropriate; stripe... Best
Tool API Mapping	Partial14/15Tools map cleanly 1:1 to individual sandbox operations (create, destroy, execute, file operations, git operations, previ... Best	Partial12/15Most tools map 1:1 to API operations (stripe_api_search, stripe_api_read, stripe_api_write, stripe_api_details), but str...
Description Clarity	Partial13/15Tool descriptions are clear and specific about their purpose; most explain what they do and expected inputs/outputs, tho... Best	Partial13/15Tool descriptions are generally clear with explicit guidance on when to use each tool (e.g., stripe_implementation_plann... Best
Eval Details
Integration task	# Task Using the Daytona MCP, manage cloud sandboxes: 1. Discover available MCP tools and their capabilities 2. List all existing sandboxes (or environments/workers/deployments)...	# Task Using the Stripe MCP, create payment resources: 1. Discover available MCP tools and their capabilities 2. Create a product called "Pro Plan" using the MCP tools 3. Create...
Generated files	1	1
Trace tool calls	27	12
Completed	9/27/2026	9/27/2026
Stderr	None captured	None captured