Causal Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
95Accuracy
63
Jun 4, 2026
94.4Accuracy
55
May 29, 2026
78Accuracy (BBH Causal Judgement)
40
Jun 2, 2026
96.4Accuracy (th)
31
Jun 1, 2026
95Performance P0
27
Jun 16, 2026
97.5Accuracy
22
May 28, 2026
82.7Accuracy
20
May 26, 2026
82.3P0 Score
14
Jun 16, 2026
80.4Accuracy
14
May 26, 2026
73.9Accuracy
14
May 26, 2026
79.8Accuracy
14
May 26, 2026
55.2Accuracy (Causal Reasoning)
14
May 26, 2026
99Accuracy (ZH)
14
Apr 21, 2026
0.465NLL
14
Feb 26, 2026
86.9Accuracy
14
Feb 26, 2026
82.3P0 Score
13
Jun 16, 2026
98P0 Score
13
Jun 16, 2026
55.5Accuracy (zh)
12
Feb 26, 2026
83Accuracy
12
Feb 26, 2026
80.2Accuracy
10
May 26, 2026
81.2Accuracy
10
May 26, 2026
80.7Accuracy (W/O Noise)
10
May 7, 2026
45.45Average F1 Score
10
Feb 26, 2026
99.89Exact Match
9
Mar 24, 2026
71.8Accuracy
8
Feb 26, 2026