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

Natural Language Inference on ANLI R2 1.0 (test)

0.331Weighted F1

ChaosNLI HJD

0.160440.204720.2490.29328Dec 18, 2024
Updated 3mo ago

Evaluation Results

MethodLinks
2024.12
0.331
2024.12
0.33
2024.12
0.324
2024.12
0.324
2024.12
0.324
2024.12
0.311
2024.12
0.297
2024.12
0.295
2024.12
0.294
2024.12
0.293
2024.12
0.289
2024.12
0.289
2024.12
0.287
2024.12
0.285
2024.12
0.283
2024.12
0.283
2024.12
0.282
2024.12
0.282
2024.12
0.276
2024.12
0.275
2024.12
0.269
2024.12
0.263
2024.12
0.262
2024.12
0.262
2024.12
0.26
2024.12
0.259
2024.12
0.176
2024.12
0.167