Financial Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77.6Accuracy
69
May 26, 2026
50.67Accuracy
46
Jun 11, 2026
70Accuracy
32
Jun 11, 2026
96.51Accuracy
27
Jun 12, 2026
85.7Accuracy
23
Mar 10, 2026
52.45Accuracy
11
Mar 4, 2026
87.14Accuracy
10
Apr 21, 2026
73.4DBS
9
Feb 26, 2026
86.72Score
7
Feb 26, 2026
82DRS
6
May 18, 2026
74.9Overall Average Accuracy
5
Jun 2, 2026
66Accuracy (Steps)
5
Jun 2, 2026
90.5Accuracy (Correct/Complete Steps)
5
Jun 2, 2026
96.3Accuracy
5
Jun 2, 2026
54.2Accuracy
5
Jun 2, 2026
80.8Performance Change vs. SAS
1
Jul 7, 2026
—
—Primary metric
0
Jun 19, 2026
—
—Primary metric
0
Jun 19, 2026