BBH
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
BBH
95.4Accuracy
770
BBH
100Accuracy
249
BBH
93.2Accuracy
190
BBH
94.6BBH General Reasoning Accuracy
117
BBH
90.5Accuracy
99
BBH (test)
73.9Accuracy
94
BBH Induct
91.3Accuracy
80
BBH
84.5BBH Score
53
BBH
74.99BBH Accuracy
51
BBH
81.1Score
51
BBH 3-shot
65.69BBH 3-shot Score
49
BBH
83.69BBH Pass@1
49
BBH
67.56Accuracy
42
BBH (val)
65.81Accuracy
42
BBH Causal Judgement
78Accuracy (BBH Causal Judgement)
40
BBH
67.1Accuracy
40
BBH
87.39Accuracy
39
BBH Navigate
98Accuracy@1
33
BBH
94.6Accuracy
33
BBH (test)
88.29Top@1 Accuracy
29
BBH
89.14Accuracy (%)
28
BBH
76.7Accuracy (BBH)
28
BBH Ded.
92.5Accuracy
28
BBH
58.27Accuracy
27
BBH
66.2Accuracy (BBH)
24