Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Unseen Perturbation Prediction on Jurkat (test)
Loading...
0.648
Pearson Delta
Exp Reprod.
0.48368
0.52634
0.569
0.61166
Jun 7, 2026
Pearson Delta
Retrieval
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pearson Delta
Retrieval
Exp Reprod.
2026.06
0.648
96.4
LLM, RL, + KG
base model=Qwen3-4B-In...
2026.06
0.51
73.7
TxPert
2026.06
0.506
68.9
LLM+KG
frontier LLM=Gemini 2....
2026.06
0.497
73.8
KG
description=graph neig...
2026.06
0.49
71.8
Feedback
Search any
task
Search any
task