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

Jina AI

Deepgram

Voice STT

Summary

Compare status

Comparable

Overall score

Best

Grade

Category

Voice STT

Overall rank

Best

#47

Category rank

Best

Full eval

Open report

MCP Task Scoring

Task score

84%

Best

31%

Task

Passed+30The agent successfully completed all required task steps: (1) discovered and described the three available MCP tools (se...

Best

Failed+0The agent correctly attempted to use MCP tools as required (mcp__deepgram__list_mcp_resources, mcp__codex__list_mcp_reso...

Used MCP Correctly

Passed+20Agent made 5 MCP tool calls

Best

Passed+20Agent made 5 MCP tool calls

Best

Partial Credit

Passed+10Partial credit: 100%

Best

Failed+0Partial credit: 0%

Zero Errors

Passed+10No errors

Best

Failed+0Tool outputs with errors: 5

Efficiency

Partial+67 tool calls (<=10, great)

Best

Partial+3.515 tool calls (<=15, good)

Time

Partial+2.0190s (3-5min, slow)

Best

Partial+2.0242s (3-5min, slow)

Best

Cost

Partial+6$0.16 ($0.10-0.20, great)

Best

Partial+6$0.12 ($0.10-0.20, great)

Best

Runtime (actual)

3m 10s

Best

4m 1s

Cost (actual)

$0.1627

$0.1215

Best

Tool calls

Best

Errors

Best

Tokens used

342,770

Best

567,330

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

Passed10/1012 tools, lean

Best

Passed10/103 tools, lean

Best

Tool Description Length

Partial7/102,033 tokens, moderate

Passed10/1029 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, tokens, or credentials visible in descriptions or schemas; parameters are clearly typed and constrained; mi...

—

Tool API Mapping

Partial14/15Tools map cleanly 1:1 to individual API operations (search_web, read_url, capture_screenshot_url, etc.), with each tool...

—

Description Clarity

Partial14/15Descriptions are clear and action-oriented, explaining what each tool does and when to use it; most include practical gu...

—

Eval Details

Integration task

# Task Using the Jina AI MCP, run a small research workflow: 1. Discover available MCP tools and their capabilities 2. Run TWO related searches to build a picture of a topic:...

# Task Using the Deepgram MCP, transcribe audio. 1. Discover the MCP tools relevant to transcription 2. Transcribe this sample audio file: https://storage.googleapis.com/aai-w...

Generated files

Trace tool calls

Completed

9/27/2026

Stderr

None captured

Metric	Jina AI Search	Deepgram Voice STT
Summary
Compare status	Comparable	Comparable
Overall score	85 Best	38
Grade	B	D
Category	Search	Voice STT
Overall rank	#7 Best	#47
Category rank	#2	#1 Best
Full eval	Open report	Open report
MCP Task Scoring
Task score	84% Best	31%
Task	Passed+30The agent successfully completed all required task steps: (1) discovered and described the three available MCP tools (se... Best	Failed+0The agent correctly attempted to use MCP tools as required (mcp__deepgram__list_mcp_resources, mcp__codex__list_mcp_reso...
Used MCP Correctly	Passed+20Agent made 5 MCP tool calls Best	Passed+20Agent made 5 MCP tool calls Best
Partial Credit	Passed+10Partial credit: 100% Best	Failed+0Partial credit: 0%
Zero Errors	Passed+10No errors Best	Failed+0Tool outputs with errors: 5
Efficiency	Partial+67 tool calls (<=10, great) Best	Partial+3.515 tool calls (<=15, good)
Time	Partial+2.0190s (3-5min, slow) Best	Partial+2.0242s (3-5min, slow) Best
Cost	Partial+6$0.16 ($0.10-0.20, great) Best	Partial+6$0.12 ($0.10-0.20, great) Best
Runtime (actual)	3m 10s Best	4m 1s
Cost (actual)	$0.1627	$0.1215 Best
Tool calls	7 Best	15
Errors	0 Best	5
Tokens used	342,770 Best	567,330
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	Passed10/1012 tools, lean Best	Passed10/103 tools, lean Best
Tool Description Length	Partial7/102,033 tokens, moderate	Passed10/1029 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, tokens, or credentials visible in descriptions or schemas; parameters are clearly typed and constrained; mi...	—
Tool API Mapping	Partial14/15Tools map cleanly 1:1 to individual API operations (search_web, read_url, capture_screenshot_url, etc.), with each tool...	—
Description Clarity	Partial14/15Descriptions are clear and action-oriented, explaining what each tool does and when to use it; most include practical gu...	—
Eval Details
Integration task	# Task Using the Jina AI MCP, run a small research workflow: 1. Discover available MCP tools and their capabilities 2. Run TWO related searches to build a picture of a topic:...	# Task Using the Deepgram MCP, transcribe audio. 1. Discover the MCP tools relevant to transcription 2. Transcribe this sample audio file: https://storage.googleapis.com/aai-w...
Generated files	1	1
Trace tool calls	7	15
Completed	9/27/2026	9/27/2026
Stderr	None captured	None captured