List your company

Automated Metric Evaluation on Scientific QA LitQA2 (n=58)

1CoverageDynRub-FT
0.65680.74590.8350.9241Jun 22, 2026

Evaluation results

MethodLinks
DynRub-FTmode=single-pass, temperature=02026.0610.3500.270.270.950.270.070.270.04
Litmusmode=single-pass, temperature=02026.0610.320.010.710.720.940.720.430.710.001
DynRub-INSTmode=single-pass, temperature=02026.060.830.1500.060.060.950.060.120.061
AutoMetricsmode=single-pass, temperature=02026.060.670.190.140.680.690.920.470.240.420.001
DynRub-DSmode=single-pass, temperature=02026.060.670.3500.120.120.950.120.230.121