← Back to context Comment by johnhess 7 days ago Was this an out of sample test of the router or was it trained on these specific use cases/eval suites? 1 comment johnhess Reply swiftcoder 6 days ago Neither. They ran all the cases using both models, picked the winning result for each one, and then said "if you had a router that guessed with 100% accuracy, here's what it would have picked"
swiftcoder 6 days ago Neither. They ran all the cases using both models, picked the winning result for each one, and then said "if you had a router that guessed with 100% accuracy, here's what it would have picked"
Neither. They ran all the cases using both models, picked the winning result for each one, and then said "if you had a router that guessed with 100% accuracy, here's what it would have picked"