Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on Helpful
Loading...
90.21
Accuracy
NWCAD
21.6948
39.4824
57.27
75.0576
Apr 17, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
NWCAD
Model=Llama-3.1-70B
2026.04
90.21
AdaCAD
Model=Llama-3.1-70B
2026.04
89.91
CoCoA
Model=Llama-3.1-70B
2026.04
87.54
NWCAD
Model=Llama-3.1-8B
2026.04
86.16
AdaCAD
Model=Llama-3.1-8B
2026.04
86.05
With-context
Model=Llama-3.1-8B
2026.04
85.46
NWCAD
Model=Ministral-3-8B
2026.04
85.16
With-context
Model=Ministral-3-8B
2026.04
84.27
AdaCAD
Model=Ministral-3-8B
2026.04
83.68
CoCoA
Model=Llama-3.1-8B
2026.04
83.09
With-context
Model=Llama-3.1-70B
2026.04
82.8
CAD
Model=Ministral-3-8B
2026.04
80.42
CAD
Model=Llama-3.1-8B
2026.04
78.04
CAD
Model=Llama-3.1-70B
2026.04
76.56
CoCoA
Model=Ministral-3-8B
2026.04
72.7
Baseline
Model=Llama-3.1-70B
2026.04
27
Baseline
Model=Ministral-3-8B
2026.04
26.11
Baseline
Model=Llama-3.1-8B
2026.04
24.33
Feedback
Search any
task
Search any
task