# Classification on Amazon Geology 8-shot (test) Source: [Classification on Amazon Geology 8-shot (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:51:31.236Z Evaluation of general Classification performance on the test split of the Amazon Geology 8-shot dataset, measured using Macro-F1 and Micro-F1 scores. 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 | Classification | | Dataset (including any stated split) | Amazon Geology 8-shot (test) | | Metric | Macro F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Macro F1 Score](): Higher is better; unit: PERCENT. - [Micro F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Macro F1 Score | Result date | Report paper | | --- | --- | --- | --- | | SCIPATTON | 39.65 | Not recorded | 68fa6f741e209131cea45b35 | | PATTON | 39.35 | Not recorded | 68fa6f741e209131cea45b35 | | SimCSE.in-domain | 38.91 | Not recorded | 68fa6f741e209131cea45b35 | | SimCSE (unsup) | 38.78 | Not recorded | 68fa6f741e209131cea45b35 | | w/o NMLM | 38.78 | Not recorded | 68fa6f741e209131cea45b35 | | w/o MNP | 38 | Not recorded | 68fa6f741e209131cea45b35 | | SciBERT.MLM | 36.94 | Not recorded | 68fa6f741e209131cea45b35 | | BERT.MLM | 36.31 | Not recorded | 68fa6f741e209131cea45b35 | | SPECTER | 30.4 | Not recorded | 68fa6f741e209131cea45b35 | | SciBERT | 29.49 | Not recorded | 68fa6f741e209131cea45b35 | | SimCSE (sup) | 25.66 | Not recorded | 68fa6f741e209131cea45b35 | | LinkBERT | 24.08 | Not recorded | 68fa6f741e209131cea45b35 | | GraphFormers | 22.64 | Not recorded | 68fa6f741e209131cea45b35 | | BERT | 21.97 | Not recorded | 68fa6f741e209131cea45b35 | ### SCIPATTON Macro F1 Score: 39.65. Result ID: 6990c0393a6c31484902feba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot","Backbone":"SciBERT"}. This record does not assert independent reproduction. ### PATTON Macro F1 Score: 39.35. Result ID: 6990c0393a6c31484902feb9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### SimCSE.in-domain Macro F1 Score: 38.91. Result ID: 6990c0393a6c31484902feb8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### SimCSE (unsup) Macro F1 Score: 38.78. Result ID: 6990c0393a6c31484902feb3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### w/o NMLM Macro F1 Score: 38.78. Result ID: 6990c0393a6c31484902febb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### w/o MNP Macro F1 Score: 38. Result ID: 6990c0393a6c31484902febc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### SciBERT.MLM Macro F1 Score: 36.94. Result ID: 6990c0393a6c31484902feb7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### BERT.MLM Macro F1 Score: 36.31. Result ID: 6990c0393a6c31484902feb6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### SPECTER Macro F1 Score: 30.4. Result ID: 6990c0393a6c31484902feb2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### SciBERT Macro F1 Score: 29.49. Result ID: 6990c0393a6c31484902feb1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### SimCSE (sup) Macro F1 Score: 25.66. Result ID: 6990c0393a6c31484902feb4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### LinkBERT Macro F1 Score: 24.08. Result ID: 6990c0393a6c31484902feb5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### GraphFormers Macro F1 Score: 22.64. Result ID: 6990c0393a6c31484902feb0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. ### BERT Macro F1 Score: 21.97. Result ID: 6990c0393a6c31484902feaf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"evaluation\_protocol":"8-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.