GLUE
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Natural Language Understanding | GLUE | SST-2156 | 531 | |
| Natural Language Understanding | GLUE (dev) | SST-2 (Acc)97.36 | 518 | |
| Natural Language Understanding | GLUE (test) | SST-2 Accuracy97.9 | 416 | |
| Natural Language Understanding | GLUE (val) | SST-297.4 | 191 | |
| Natural Language Understanding | GLUE (test dev) | MRPC Accuracy93.45 | 87 | |
| General Language Understanding | GLUE | Accuracy92.5 | 66 | |
| Model Merging | GLUE CoLA, MRPC, RTE, SST-2 | Absolute Accuracy75.9 | 60 | |
| Natural Language Understanding | GLUE (test val) | MRPC Accuracy94 | 59 | |
| Natural Language Understanding | GLUE | SST-295.18 | 55 | |
| Natural Language Understanding | GLUE | COLA Score69.3 | 41 | |
| General Language Understanding | GLUE v1 (test dev) | MNLI87.86 | 40 | |
| Natural Language Understanding | GLUE (test) | MNLI-mm98.6 | 39 | |
| Natural Language Understanding | GLUE (test) | SST-2 Accuracy95.64 | 33 | |
| Natural Language Understanding | GLUE small | CoLA Mcc73.4 | 32 | |
| Adversarial Attack | GLUE | SST-2 Speedup3.56 | 32 | |
| Natural Language Understanding | GLUE | SST-2 Speedup3.06 | 32 | |
| Natural Language Understanding | GLUE v1 (dev) | MRPC Score93.8 | 30 | |
| Natural Language Understanding | GLUE | SST-2 Acc97.5 | 28 | |
| Text classification | GLUE | Average Score87.6 | 28 | |
| Natural Language Understanding | GLUE 1.0 (test) | SST-2 (Acc)97.8 | 28 | |
| Natural Language Understanding | GLUE (test) | QNLI Score92.31 | 26 | |
| Binary classification | GLUE (test) | QNLI Accuracy90.66 | 25 | |
| Natural Language Understanding | GLUE | MNLI Accuracy61.58 | 24 | |
| Natural Language Understanding | GLUE MNLI MRPC QNLI QQP SST2 standard (test) | MNLI Accuracy88.08 | 24 | |
| Natural Language Understanding | GLUE (test) | QNLI7,564.6 | 23 |
Showing 25 of 136 rows