mstoeck3/llm-eval-forensics
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

improvements

Browse Source
This commit is contained in:
Mario Stöckl
2026-01-16 15:24:34 +01:00
parent 345aa419c7
commit 5d8deb1e3c
2 changed files with 84 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
analyze_results.py
View File

@@ -487,11 +487,18 @@ class WebInterface:
dimensions = {
'logical_reasoning': ['Logic & Reasoning'],
'mathematical_ability': ['Mathematics & Calculation'],
'instruction_following': ['Instruction Following'],
'instruction_following': ['Instruction Following', 'Multi-turn: Instruction Following'],
'creativity': ['Creative Writing'],
'technical_knowledge': ['Code Generation', 'IT Forensics'],
'linguistic_nuance': ['Language Nuance'],
'conversational_depth': ['Multi-turn Conversations']
'technical_knowledge': [
'Code Generation',
'IT Forensics - File Systems',
'IT Forensics - Registry & Artifacts',
'IT Forensics - Memory & Network',
'IT Forensics - Timeline & Log Analysis'
],
'linguistic_nuance': ['Language Nuance', 'Multilingual Competence'],
'problem_solving': ['Problem Solving & Logistics'],
'conversational_depth': ['Multi-turn: Context Retention']
}
model_metrics = {}
@@ -527,6 +534,7 @@ class WebInterface:
'creativity': 1.0,
'technical_knowledge': 1.4,
'linguistic_nuance': 1.1,
'problem_solving': 1.4,
'conversational_depth': 1.0
}