LLM Routing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.67nAUC
9
Feb 26, 2026
75.6nAUC
9
Feb 26, 2026
0.023Cost (Cost-first)
8
Apr 13, 2026
82Accuracy
8
Mar 4, 2026
97Accuracy
8
Mar 4, 2026
179.75Loss
7
Jun 4, 2026
2.3Cost (Cost-first)
7
Apr 13, 2026
0.624LPM
7
Feb 26, 2026
59.2LPM
7
Feb 26, 2026
51.74LPM
7
Feb 26, 2026
59.2LPM
7
Feb 26, 2026
69.24LPM Score
7
Feb 26, 2026
63.53LPM Score
7
Feb 26, 2026
78.51LPM
7
Feb 26, 2026
65.32STEM Score
7
Feb 26, 2026
73.9AUROC
7
Feb 26, 2026
74.08AUROC
7
Feb 26, 2026
0.679AUROC
7
Feb 26, 2026
0.662AUROC
7
Feb 26, 2026
0.72AUROC
7
Feb 26, 2026
0.867HV
6
Jun 5, 2026
75.48HV
6
Jun 5, 2026
0.841HV Score
6
Jun 5, 2026
0.851HV Score
6
Jun 5, 2026
86.97HV Score
6
Jun 5, 2026