Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Predictive LLM Routing on AlpacaEval

63.17Score (vs OpenAI)

Oracle

35.40242.61149.8257.029May 19, 2025
Updated 16d ago

Evaluation Results

MethodLinks
2025.05
63.1752.9834.69
2025.05
57.652.8434.26
2025.05
57.552.8434.2
2025.05
57.3852.7734.26
2025.05
57.3751.8432.25
2025.05
57.3352.8234.27
2025.05
57.1752.7724.45
2025.05
56.8552.0833.76
2025.05
55.6645.6431.5
2025.05
55.551.2932.18
2025.05
55.2952.4927.94
2025.05
54.7151.1430.96
2025.05
54.6151.1430.96
2025.05
54.6151.1430.96
2025.05
54.5451.1430.96
2025.05
54.5251.1430.95
2025.05
54.544.6229.34
2025.05
54.4345.1226.52
2025.05
54.0851.1430.91
2025.05
54.0451.1430.96
2025.05
53.8451.1430.91
2025.05
53.5551.1430.96
2025.05
50.8151.1430.52
2025.05
38.3242.0423.72
2025.05
37.8943.9923.88
2025.05
36.4734.5627.76