Waifmark 2 Benchmarking Suite
API docs
01Model SearchFind a model to Benchmark

Waifmark 2 Control Center

Search Hugging Face or directly import GGUF to find your model. Run agentic & roleplay benchmarks, and audit with llm-as-a-judge.
See the leaderboard →

View Leaderboard →
Press 1–4 or use navbar to quickly adjust your workspace.
Leaderboard Top 3
#Model / Repo IDAuthorDownloads
Downloaded Models

        
        

          
Import Local Weights

          
Directly use a GGUF / HF folder already on this machine

          

          

            

            

          

          
          

        

      

    

  


  
  

    
02ConfigExpandable • Import/Export

    

      

        

          
          
          
        

        

          
          
          
          
          
        

      

      

      

      
Raw YAML (advanced)

      
    

  


  
  

    
03BenchmarkRun • Live log uses full viewport

    

      

        

        

        

      

      

        
        
        
        
        
        
      

      

        
Statusidle

        
Progress0/0

        
Scores (A / R / Overall)--

        
ETA—

      

      

    

    

      

        
Live LogVerbose

        
No live log yet.

        
Server logs

      

      

        

          
Past Runs

          
CSV

        

        

        

        
ModuleTaskScoreReview

        

      

    

  


  
  

    
04Human AuditSegmented filter makes bulk scope explicit

    

      

        0 items
        Search narrows current segment; bulk acts on filtered view
      

      

        

          

            
            
            
          

          
        

        

          
          
        

      

    

    

      

        

        

        
      

      

        
        

          

            

            

          

          
          

        

        
        
Select an item.