Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Groundedness on HaluEval
Loading...
0.78
Kendall's Tau
GPT-OSS-120B
0.1144
0.2872
0.46
0.6328
Dec 1, 2025
Kendall's Tau
Standard Deviation
Updated 4d ago
Evaluation Results
Method
Method
Links
Kendall's Tau
Standard Deviation
GPT-OSS-120B
Judge Model=GPT-OSS-120B
2025.12
0.78
0.03
Jury-on-Demand
2025.12
0.77
0.02
GPT-OSS-20B
Judge Model=GPT-OSS-20B
2025.12
0.76
0.03
Gemini 2.5 Flash
Judge Model=Gemini 2.5...
2025.12
0.74
0.04
Gemini 2.5 Pro
Judge Model=Gemini 2.5...
2025.12
0.73
0.03
Claude 3.7
Judge Model=Claude 3.7
2025.12
0.67
0.04
Gemini 2.0 Flash
Judge Model=Gemini 2.0...
2025.12
0.52
0.03
DeepSeek R1
Judge Model=DeepSeek R1
2025.12
0.4
0.03
LLAMA 3.2
Judge Model=LL-3.2
2025.12
0.2
0.05
Gemma 3
Judge Model=Gemma 3
2025.12
0.17
0.04
Phi 4
Judge Model=Phi 4
2025.12
0.14
0.05
Feedback
Search any
task
Search any
task