Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
68.97Accuracy
7
Mar 25, 2026
72.8Avg Acc
7
Feb 26, 2026
46.21Humanities Score
7
Feb 26, 2026
0.757Astronomy Accuracy
7
Feb 26, 2026
22.9ARC-Challenge Acc
7
Feb 26, 2026
18.5Math Score (MMLU-Pro)
6
Jun 8, 2026
80.92Biology Avg@16
6
Jun 2, 2026
58.3Accuracy
6
Jun 1, 2026
4.87Accuracy
6
May 26, 2026
48.41Logic Accuracy
6
May 22, 2026
90.13Selection Accuracy
6
Apr 21, 2026
91.71Score
6
Apr 21, 2026
56pass@1
6
Apr 15, 2026
74Pass@1
6
Apr 15, 2026
96.15SST-2 Score
6
Apr 6, 2026
52.61Average Score
6
Feb 26, 2026
60Average Score
6
Feb 26, 2026
0.692Accuracy
6
Feb 26, 2026
70.56Belebele-pt Accuracy
6
Feb 26, 2026
43.3Avg Performance
6
Feb 26, 2026
53.09BLEU-4
6
Feb 26, 2026
0.92ΔMMLU
5
Jun 19, 2026
66.7Reward
5
Jun 8, 2026
77.4Reward
5
Jun 8, 2026
89.8MMLU Biology Score
5
May 19, 2026