Eval Suites
Total Suites
3
Avg Pass Rate
91.3%
Total Regressions
5
Code Generation Accuracy
87.5%Tests agent ability to generate syntactically correct and logically sound code
Last run: Aug 22, 2026 at 6:00 PM
42/48
tests passing
2 Regressions
Generate React hooks with dependencies
Missing cleanup function in 3/5 cases
Async error handling
Missing try-catch blocks
Security Review Completeness
92.3%Evaluates agent detection of common security vulnerabilities
Last run: Aug 23, 2026 at 8:30 AM
36/39
tests passing
1 Regression
Detect SQL injection in raw queries
Missed parameterization issue in helper function
Documentation Quality
94.1%Measures clarity, accuracy, and completeness of generated documentation
Last run: Aug 22, 2026 at 3:15 PM
32/34
tests passing
2 Regressions
API endpoint examples
Outdated authentication example
Type documentation
Missing generic constraints