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

Performance Prediction on Reasoning Benchmarks Average

0.874Train R^2

RBRIDGE

0.16680.35040.5340.7176Sep 25, 2025
Updated 23d ago

Evaluation Results

MethodLinks
2025.09
0.8741.384
2025.09
0.8671.455
2025.09
0.8461.304
2025.09
0.8261.481
2025.09
0.821.549
2025.09
0.821.54
2025.09
0.5174.236
2025.09
0.4883.276
2025.09
0.4855.173
2025.09
0.4133.932
2025.09
0.3753.377
2025.09
0.3523.546
2025.09
0.3495.165
2025.09
0.3294.375
2025.09
0.31219.785
2025.09
0.3043.709
2025.09
0.3025.251
2025.09
0.295.123
2025.09
0.25727.062
2025.09
0.20521.833
2025.09
0.194302.642