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
Claude CodeClaude CodeCodexCodex
Tooling
APICLIMCP

Choose 2-4 companies

Selected
Qdrant
Exa
Showing the first two companies on mobile. Use a wider screen to compare 3 companies.
Mobile compare is limited to two companies. Use a wider screen to compare all 3.
Qdrant

Qdrant

Vector Databases

Exa

Exa

Search

Summary

Compare status

Comparable
No tokens used recorded

Overall score

80
—

Grade

B
—

Category

Vector Databases
Search

Overall rank

#13
—

Category rank

#1
—

Full eval

Open report
Open report
Agent Performance

Eval score

72%
—

Task success

Yes
—

Cost

$0.3745
—

Tool calls

44
—

Errors

12
—

Runtime

1m 44s
—

Tokens used

1,799,393
—

Exit code

0
—
Discoverability

Discovery score

100%
—

Context7

Yes
—

llms.txt

Yes
—

MCP Server

Yes
—

Typed SDK

Yes
—

OpenAPI

Yes
—

Agent Skills

Yes
—

CLI

Yes
—
Eval Details

Integration task

# Task Using https://qdrant.tech/documentation, complete the following task: Using Qdrant, build me a FAQ search system: 1. Store these 3 FAQs: - Q: "How do I reset my passwo...
—

Generated files

2
—

Trace tool calls

44
—

Completed

9/27/2026
—

Stderr

None captured
—