List your company

Metric Correlation Analysis on Synthetic perturbation sets (test)

80.27Spearman's rho (S)TABXEVAL
27.781241.408155.03568.6619Dec 17, 2025

Evaluation results

MethodLinks
TABXEVALMetric Category=LLM-Based, Reference=With Reference2025.1280.2772.3766.8747.5420.9445.33
TABREXMetric Category=Reference-less, Reference=Reference-less2025.1274.5164.2462.2844.8527.0113.59
QUESTEVALMetric Category=Reference-less, Reference=Reference-less2025.1262.9352.2951.7142.735.043.03
H-SCOREMetric Category=Non-LLM Based, Reference=With Reference2025.1256.8747.9751.7341.1140.020.99
LLM EnsembleEnsemble Type=LLM-based, Aggregation=Harmonic Mean (H)2025.125646.9350.6440.9540.630.42
Hybrid EnsembleEnsemble Type=Reference + Reference-less, Aggregation=Harmonic Mean (H)2025.1254.0342.7132.6142.3140.111.13
P-SCOREMetric Category=LLM-Based, Reference=With Reference2025.1249.244037.4340.7343.937.39
TABEVALMetric Category=LLM-Based, Reference=With Reference2025.1249.0139.2234.2141.1143.060.63
LLM EnsembleEnsemble Type=LLM-based, Aggregation=Simple Mean (M)2025.1248.4939.2136.9440.5644.380.42
EMMetric Category=Non-LLM Based, Reference=With Reference2025.1245.8839.3839.5143.3347.4958.4
BLUERTMetric Category=Non-LLM Based, Reference=With Reference2025.1244.6637.6436.0939.5748.090.77
CHRFMetric Category=Non-LLM Based, Reference=With Reference2025.1241.7634.5531.6139.3949.261.64
Lex-EmbEnsemble Type=Lexical + Embedding, Aggregation=Simple Mean (M)2025.1238.4332.6530.1738.5252.150.49
BERTSCOREMetric Category=Non-LLM Based, Reference=With Reference2025.1236.2130.6627.9638.1153.250.92
Hybrid EnsembleEnsemble Type=Reference + Reference-less, Aggregation=Simple Mean (M)2025.1232.0424.9420.2937.0351.511.13
ROUGE-LMetric Category=Non-LLM Based, Reference=With Reference2025.1231.1826.6922.5637.6555.941.97
Lex-EmbEnsemble Type=Lexical + Embedding, Aggregation=Harmonic Mean (H)2025.1229.82419.6837.6555.040.63