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

OR-BIAS-BENCH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Operations Research ReasoningOR-BIAS-BENCH OOD
Rationality100
24
Operations Research ReasoningOR-BIAS-BENCH ID
Rationality100
24
Rational Ordering EvaluationOR-BIAS-BENCH OOD 200 samples
Bias0.036
7
Rational Ordering EvaluationOR-BIAS-BENCH 400 samples (In-Distribution)
Bias0
7
Behavioral Rationality EvaluationOR-Bias-Bench
Bias Difference10.4
2
Showing 5 of 5 rows