github/toon
1
0
Fork 0
mirror of https://github.com/voson-wang/toon.git synced 2026-01-29 15:24:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(benchmarks): replace LLM-as-judge, new structural validation

Browse Source
This commit is contained in:
Johann Schopplich
2025-11-07 21:28:21 +01:00
parent 9a519dd114
commit acca69c64a
25 changed files with 1311 additions and 396 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
benchmarks/src/constants.ts
View File

@@ -56,9 +56,11 @@ export const FORMATTER_DISPLAY_NAMES: Record<string, string> = {
*/
export const QUESTION_TYPES = [
'field-retrieval',
'retrieval',
'aggregation',
'filtering',
'structure-awareness',
'structural-validation',
] as const
/**
@@ -66,9 +68,11 @@ export const QUESTION_TYPES = [
*/
export const QUESTION_TYPE_LABELS = {
'field-retrieval': 'Field Retrieval',
'retrieval': 'Retrieval',
'aggregation': 'Aggregation',
'filtering': 'Filtering',
'structure-awareness': 'Structure Awareness',
'structural-validation': 'Structural Validation',
} as const
/**
@@ -81,6 +85,12 @@ export const DATASET_NAMES = [
'github',
'event-logs',
'nested-config',
'large-uniform',
'structural-validation-control',
'structural-validation-truncated',
'structural-validation-extra-rows',
'structural-validation-width-mismatch',
'structural-validation-missing-fields',
] as const
/**