quetzal-eval

0.2.0 Not latest — view latest

Measure how well and how cheaply a coding-agent harness answers questions about your codebase. Drives real agent CLIs (Claude Code, Codex, Cursor), judges answers against ground truth, and reports accuracy + token cost per suite.

License Sources Match

MIT confirmed by 2 independent sources — Python registry metadata and the LICENSE file in the package source — as of July 2, 2026.

SourceLicenseClass
Licensie (detected)
MITPermissive
PyPI (reported)
MITPermissive
Loading dependencies…
License File
Added Removed Expected
Versions
7 versions
VersionLicensePublishedStatus
0.2.3 Latest MITJul 2, 2026 Scanned
0.2.2 MITJul 2, 2026 Scanned
0.2.1 MITJul 2, 2026 Scanned
0.2.0 ViewingMITJul 2, 2026 Scanned
0.1.2 MITJul 1, 2026 Scanned
0.1.1 MITJul 1, 2026 Scanned
0.1.0 MITJul 1, 2026 Scanned