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:
overcuriousity
2026-01-18 15:14:25 +01:00
parent 9853faf09b
commit 7697bb51ab
4 changed files with 1481 additions and 945 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
analyze_results.py
View File

@@ -507,18 +507,14 @@ class WebInterface:
dimensions = {
'logical_reasoning': ['Logic & Reasoning'],
'mathematical_ability': ['Mathematics & Calculation'],
'instruction_following': ['Instruction Following', 'Multi-turn: Instruction Following'],
'creativity': ['Creative Writing'],
'instruction_following': ['Instruction Following with Constraints'],
'creativity': ['Creative Writing with Constraints'],
'technical_knowledge': [
'Code Generation',
'IT Forensics - File Systems',
'IT Forensics - Registry & Artifacts',
'IT Forensics - Memory & Network',
'IT Forensics - Timeline & Log Analysis'
'Code Generation - Advanced',
'Digital Forensics & Binary Analysis'
],
'linguistic_nuance': ['Language Nuance', 'Multilingual Competence'],
'problem_solving': ['Problem Solving & Logistics'],
'conversational_depth': ['Multi-turn: Context Retention']
'linguistic_nuance': ['Language Understanding & Pragmatics'],
'conversational_depth': ['Multi-turn Context & Instruction Handling']
}
model_metrics = {}