# Text Classification on Amazon Review 1000 labels (test) Source: [Text Classification on Amazon Review 1000 labels (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:19.592Z Evaluation of Text Classification performance on the 1000-label test split of the Amazon Review dataset. 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 | Text Classification | | Dataset (including any stated split) | Amazon Review 1000 labels (test) | | Metric | Top-1 Error Rate | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 20 of 20 | | 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 - [Top-1 Error Rate](): Lower is better; unit: PERCENT. - [Average Gain](): Higher is better; unit: SCALAR. - [Average Speedup](): Higher is better; unit: SCALAR. ## Recorded results | Method | Top-1 Error Rate | Result date | Report paper | | --- | --- | --- | --- | | SoftMatch/FreeMatch | 39.17 | Not recorded | 68fa72451e209131cea556d1 | | FlexMatch | 41.11 | Not recorded | 68fa72451e209131cea556d1 | | SoftMatch/FreeMatch | 42.21 | Not recorded | 68fa72451e209131cea556d1 | | SimMatch | 42.21 | Not recorded | 68fa75781e209131cea682ff | | SoftMatch | 42.21 | Not recorded | 68fa75781e209131cea682ff | | FlexMatch | 42.25 | Not recorded | 68fa72451e209131cea556d1 | | FlexMatch | 42.25 | Not recorded | 68fa75781e209131cea682ff | | AdaMatch | 42.27 | Not recorded | 68fa75781e209131cea682ff | | ILL | 42.32 | Not recorded | 68fa75781e209131cea682ff | | FreeMatch | 42.64 | Not recorded | 68fa75781e209131cea682ff | | FixMatch | 43.05 | Not recorded | 68fa75781e209131cea682ff | | Dash | 43.09 | Not recorded | 68fa75781e209131cea682ff | | CoMatch | 43.36 | Not recorded | 68fa75781e209131cea682ff | | Pseudo Label | 44.21 | Not recorded | 68fa72451e209131cea556d1 | | VAT | 46.54 | Not recorded | 68fa75781e209131cea682ff | | Pseudo Label | 47 | Not recorded | 68fa72451e209131cea556d1 | | Pseudo-Label | 47 | Not recorded | 68fa75781e209131cea682ff | | Mean-Teacher | 47.66 | Not recorded | 68fa75781e209131cea682ff | | MixMatch | 61.69 | Not recorded | 68fa75781e209131cea682ff | ### SoftMatch/FreeMatch Top-1 Error Rate: 39.17. Result ID: 699229363a6c3148490cffae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"+SR"}. This record does not assert independent reproduction. ### FlexMatch Top-1 Error Rate: 41.11. Result ID: 699229363a6c3148490cffac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"+SR"}. This record does not assert independent reproduction. ### SoftMatch/FreeMatch Top-1 Error Rate: 42.21. Result ID: 699229363a6c3148490cffad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Base"}. This record does not assert independent reproduction. ### SimMatch Top-1 Error Rate: 42.21. Result ID: 6993b3b23a6c31484917eddd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### SoftMatch Top-1 Error Rate: 42.21. Result ID: 6993b3b23a6c31484917eddf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### FlexMatch Top-1 Error Rate: 42.25. Result ID: 699229363a6c3148490cffab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Base"}. This record does not assert independent reproduction. ### FlexMatch Top-1 Error Rate: 42.25. Result ID: 6993b3b23a6c31484917edda. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### AdaMatch Top-1 Error Rate: 42.27. Result ID: 6993b3b23a6c31484917edd8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### ILL Top-1 Error Rate: 42.32. Result ID: 6993b3b23a6c31484917ede0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### FreeMatch Top-1 Error Rate: 42.64. Result ID: 6993b3b23a6c31484917edde. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### FixMatch Top-1 Error Rate: 43.05. Result ID: 6993b3b23a6c31484917edd9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### Dash Top-1 Error Rate: 43.09. Result ID: 6993b3b23a6c31484917eddb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### CoMatch Top-1 Error Rate: 43.36. Result ID: 6993b3b23a6c31484917eddc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### Pseudo Label Top-1 Error Rate: 44.21. Result ID: 699229363a6c3148490cffaa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"+SR"}. This record does not assert independent reproduction. ### VAT Top-1 Error Rate: 46.54. Result ID: 6993b3b23a6c31484917edd6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### Pseudo Label Top-1 Error Rate: 47. Result ID: 699229363a6c3148490cffa9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Base"}. This record does not assert independent reproduction. ### Pseudo-Label Top-1 Error Rate: 47. Result ID: 6993b3b23a6c31484917edd4. [Reporting paper]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### Mean-Teacher Top-1 Error Rate: 47.66. Result ID: 6993b3b23a6c31484917edd5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. ### MixMatch Top-1 Error Rate: 61.69. Result ID: 6993b3b23a6c31484917edd7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"# Labels":1000,"Backbone":"Bert-Base"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.