Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
44Accuracy@1 (GPQA)
33
Apr 28, 2026
95.15GSM8K Accuracy
33
Mar 18, 2026
80.8Math Accuracy
33
Feb 26, 2026
78.9ARC-E Accuracy
32
Jul 7, 2026
64.1Pass@1
32
May 28, 2026
77.95Accuracy
32
Mar 4, 2026
53.98Accuracy
32
Mar 4, 2026
97.5Accuracy (Reasoning BBQ)
32
Mar 4, 2026
100Acc
32
Jun 9, 2026
71.89Accuracy
32
Jul 8, 2026
60AIME 2024 Score
32
Feb 26, 2026
68.6Average Score
32
Feb 26, 2026
98.86Accuracy
32
May 28, 2026
88.7Accuracy
31
May 19, 2026
90.97Score
31
Apr 20, 2026
57.3Accuracy
30
May 27, 2026
29.01GPQA Score
30
May 14, 2026
32.27BBH Score
30
Apr 14, 2026
34.58Avg@32
30
Apr 28, 2026
88.2Accuracy (ACC)
29
May 13, 2026
94.5ARC-c Score
29
Feb 26, 2026
94.4Accuracy
29
Jun 2, 2026
76.7Accuracy (BBH)
28
Jun 25, 2026
69.9Average Accuracy
28
Apr 30, 2026
98.1First-Token Accuracy
28
Jun 5, 2026