Multi-task Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
29.17AIME 25 Score
41
Jun 2, 2026
77.6Average Accuracy
21
Feb 26, 2026
79.4Average Accuracy
20
May 27, 2026
50.7Mean Downstream Accuracy
20
May 12, 2026
74.6Score
20
Feb 26, 2026
82.1Average Score
16
Apr 10, 2026
60.77Accuracy
13
Mar 12, 2026
74.6Average Score
12
Apr 9, 2026
51.9Avg Accuracy
10
Feb 26, 2026
51.8Overall Average
9
May 7, 2026
62.8Average Score
8
May 19, 2026
7.81Average Total Score
7
Jul 7, 2026
8.318Average Total Score
7
Jul 7, 2026
51.6Accuracy
7
May 12, 2026
40.86Average Accuracy
6
May 18, 2026
52.45Hit Score
6
Feb 26, 2026
86.7Accuracy
3
Mar 24, 2026
58.3Persuasive Strategies Score
2
Feb 26, 2026