Zero-shot Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
76.55Average Accuracy
305
Jun 15, 2026
6,540Average Reasoning Score
125
Jun 4, 2026
82.54PIQA Zero-shot Accuracy
115
Jun 4, 2026
80.51Accuracy
107
Jun 4, 2026
69.99Average Accuracy
97
Jun 29, 2026
97.43Zero-shot Accuracy
94
Jun 4, 2026
72.7Accuracy
65
May 12, 2026
82.813BoolQ Accuracy (Zero-shot)
64
Jun 23, 2026
71.57Accuracy
56
May 25, 2026
65.53ARC-C Accuracy
54
Apr 16, 2026
60.41Zero-Shot Accuracy
53
Jun 4, 2026
76.3Accuracy
53
Jun 4, 2026
57Average Accuracy
40
Jun 19, 2026
77.2Normalized Avg Accuracy
36
Feb 26, 2026
75.33Average Accuracy
34
Jun 19, 2026
28.4Accuracy
26
Apr 3, 2026
44Accuracy
26
Apr 3, 2026
32.75LAMBADA (LMB) Accuracy
22
May 20, 2026
78.07PIQA
21
Feb 26, 2026
77.1ARC-e Accuracy (Zero-shot)
20
Jun 9, 2026
62.69PiQA Score
20
Mar 25, 2026
28OpenbookQA Accuracy
18
Jul 7, 2026
80.41PIQA Accuracy
18
Mar 27, 2026
68Accuracy
17
May 28, 2026
50.43ARC-C Accuracy
14
Jun 5, 2026