Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Annotation on Annotation Task Suite Toxicity and Safety Domains (various)

84.4Accuracy

GPT-4o-mini

71.81675.08378.3581.617May 30, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
84.40.883
2026.05
84.30.883
2026.05
84.10.88
2026.05
83.80.893
2026.05
83.80.894
2026.05
83.30.89
2026.05
83.30.875
2026.05
83.30.88
2026.05
83.30.876
2026.05
83.20.892
2026.05
83.20.891
2026.05
830.904
2026.05
830.881
2026.05
82.80.86
2026.05
82.70.868
2026.05
82.70.861
2026.05
82.60.899
2026.05
82.60.89
2026.05
82.50.887
2026.05
82.40.868
2026.05
82.30.892
2026.05
82.30.879
2026.05
82.30.862
2026.05
82.20.879
2026.05
82.20.872
2026.05
82.10.888
2026.05
82.10.898
2026.05
820.896
2026.05
820.827
2026.05
81.70.825
2026.05
81.60.85
2026.05
81.60.865
2026.05
81.60.871
2026.05
81.50.852
2026.05
81.40.823
2026.05
81.30.904
2026.05
81.30.787
2026.05
81.30.874
2026.05
81.20.892
2026.05
81.20.819
2026.05
81.20.876
2026.05
81.20.843
2026.05
81.20.868
2026.05
81.10.857
2026.05
810.863
2026.05
810.868
2026.05
80.90.859
2026.05
80.90.877
2026.05
80.80.838
2026.05
80.80.87
2026.05
80.70.85
2026.05
80.70.856
2026.05
80.50.885
2026.05
80.50.858
2026.05
80.50.852
2026.05
80.10.843
2026.05
80.10.874
2026.05
79.90.889
2026.05
79.80.881
2026.05
79.70.869
2026.05
79.30.867
2026.05
790.863
2026.05
78.10.859
2026.05
780.868
2026.05
77.50.884
2026.05
770.822
2026.05
76.80.818
2026.05
76.70.832
2026.05
75.40.824
2026.05
75.30.822
2026.05
73.50.821
2026.05
72.30.809