Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
29.96Pass@1 (Reasoning)
9
May 12, 2026
94.5Accuracy (%)
9
May 1, 2026
80.5PiQA Accuracy
9
Apr 10, 2026
95.2Average Normalized Score
9
Apr 1, 2026
100Normalized Score
9
Apr 1, 2026
102.1Normalized Score
9
Apr 1, 2026
100.4Normalized Score
9
Apr 1, 2026
100Normalized Score
9
Apr 1, 2026
40EM
9
Mar 20, 2026
86.2EM
9
Mar 20, 2026
88.02Overall GSM8K Accuracy
9
Mar 12, 2026
37.14MuSR Score
9
Mar 4, 2026
37.3pass@1
9
Mar 4, 2026
85.12GSM8K Accuracy
9
Feb 27, 2026
50Accuracy
9
Apr 8, 2026
722.5Score
9
Jun 2, 2026
39.3Accuracy
9
Feb 26, 2026
52.5Accuracy
9
Feb 26, 2026
85.12GSM8K
9
Feb 27, 2026
87.23GSM8K
9
Feb 27, 2026
87.23GSM8K Accuracy
9
Feb 27, 2026
59.58Score
9
Feb 26, 2026
26.26PHYBench Score
9
Feb 26, 2026
0.279Accuracy
9
Feb 26, 2026
39.6Accuracy
9
Feb 26, 2026