Kind: Interface
Source: atloria-monorepo/libs/agent-core/src/benchmark/types.ts
Summary of a complete benchmark run.
Properties
| Property | Type |
|---|---|
suite | BenchmarkTask['suite'] |
model | string |
timestamp | string |
totalTasks | number |
passedTasks | number |
passRate | number |
totalDurationMs | number |
totalTokens | { input: number; output: number; total: number } |
totalCostUsd | number |
avgCostPerTask | number |
byDifficulty | Record<string, { total: number; passed: number; rate: number }> |
byLanguage | Record<string, { total: number; passed: number; rate: number }> |
results | TaskResult[] |
toolStats | Record<string, { count: number; avgDurationMs: number }> |
failureBreakdown | Record<string, number> |
byRepo | Record<string, { total: number; passed: number; rate: number; topFailure?: string }> |
cumulativePassAtK | Record<number, { passed: number; rate: number }> |
marginalGains | Record<string, number> |
passAtK | { k: number; passed: number; rate: number } |
passAtKResults | PassAtKResult[] |
costEfficiency | `{ |
firstPassSuccess: { avgTokens: number; avgDurationMs: number; avgTurns: number; count: number }; recoveredSuccess: { avgTokens: number; avgDurationMs: number; avgTurns: number; count: number }; finalFailure: { avgTokens: number; avgDurationMs: number; avgTurns: number; count: number };
}| |fileLocalizationStats|{
avgRecall: number;
avgPrecision: number;
/** Tasks with >0 overlap that still failed /
correctAreaButFailed: number;
/* Tasks with 0 overlap */
zeroOverlap: number;
}` |
Was this page helpful?