# Natural Language Understanding on GLUE (SST-2, QNLI, QQP, MNLI Subset) Source: [Natural Language Understanding on GLUE (SST-2, QNLI, QQP, MNLI Subset)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:03:30.880Z Evaluation of model performance across a specific subset of GLUE tasks: SST-2, QNLI, QQP, and MNLI, reporting an average score across these four components. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Natural Language Understanding | | Dataset (including any stated split) | GLUE | | Metric | SST-2 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [SST-2](): Higher is better; unit: PERCENT. - [QNLI](): Higher is better; unit: PERCENT. - [QQP](): Higher is better; unit: PERCENT. - [MNLI](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | SST-2 | Result date | Report paper | | --- | --- | --- | --- | | RoBERTa-Large (FedTT+) | 95.64 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (FedTT+) | 95.53 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (FedTT+) | 95.41 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (FFA-LoRA r=8) | 95.14 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (LoRA r=8) | 94.42 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (LoRA r=8) | 94.32 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (FFA-LoRA r=8) | 94.32 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (FFA-LoRA r=8) | 94.1 | Not recorded | 68fa79061e209131cea7bc39 | | RoBERTa-Large (LoRA r=8) | 93.55 | Not recorded | 68fa79061e209131cea7bc39 | ### RoBERTa-Large (FedTT+) SST-2: 95.64. Result ID: 6995ba373badfaffe6bb866e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"sever het.","Backbone":"RoBERTa-Large","# Param.":"0.03M"}. This record does not assert independent reproduction. ### RoBERTa-Large (FedTT+) SST-2: 95.53. Result ID: 6995ba373badfaffe6bb866b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"mild het.","Backbone":"RoBERTa-Large","# Param.":"0.03M"}. This record does not assert independent reproduction. ### RoBERTa-Large (FedTT+) SST-2: 95.41. Result ID: 6995ba373badfaffe6bb8668. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"i.i.d.","Backbone":"RoBERTa-Large","# Param.":"0.03M"}. This record does not assert independent reproduction. ### RoBERTa-Large (FFA-LoRA r=8) SST-2: 95.14. Result ID: 6995ba373badfaffe6bb8667. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"i.i.d.","Backbone":"RoBERTa-Large","# Param.":"0.79M"}. This record does not assert independent reproduction. ### RoBERTa-Large (LoRA r=8) SST-2: 94.42. Result ID: 6995ba373badfaffe6bb8666. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"i.i.d.","Backbone":"RoBERTa-Large","# Param.":"1.57M"}. This record does not assert independent reproduction. ### RoBERTa-Large (LoRA r=8) SST-2: 94.32. Result ID: 6995ba373badfaffe6bb866c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"sever het.","Backbone":"RoBERTa-Large","# Param.":"1.57M"}. This record does not assert independent reproduction. ### RoBERTa-Large (FFA-LoRA r=8) SST-2: 94.32. Result ID: 6995ba373badfaffe6bb866d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"sever het.","Backbone":"RoBERTa-Large","# Param.":"0.79M"}. This record does not assert independent reproduction. ### RoBERTa-Large (FFA-LoRA r=8) SST-2: 94.1. Result ID: 6995ba373badfaffe6bb866a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"mild het.","Backbone":"RoBERTa-Large","# Param.":"0.79M"}. This record does not assert independent reproduction. ### RoBERTa-Large (LoRA r=8) SST-2: 93.55. Result ID: 6995ba373badfaffe6bb8669. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Distribution":"mild het.","Backbone":"RoBERTa-Large","# Param.":"1.57M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.