GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
Covid variant classification, dataset Covid. Scored with F1 on GUE Covid variant classification, Covid. Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.
Overview
Covid variant classification, dataset Covid. Scored with F1 on GUE Covid variant classification, Covid. Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- DNABERT-2 on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- DNABERT-2 (further pre-trained on GUE) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- DNABERT (3-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- DNABERT (4-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- DNABERT (5-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- DNABERT (6-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- NT-2500M-1000g on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- NT-2500M-multi on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- NT-500M-1000g on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- NT-500M-human on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Published comparisons
Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.
GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
f1 (percent) · Higher values are better for this metric.
Every method GUE reports on Covid variant classification, dataset Covid, scored with F1 on GUE Covid variant classification, Covid.
Evaluation protocol · GUE Covid variant classification, Covid (GUE split)
- DNABERT (3-mer) · Configuration · Author-reported evaluation62.23
- DNABERT (4-mer) · Configuration · Author-reported evaluation59.87
- DNABERT (5-mer) · Configuration · Author-reported evaluation50.46
- DNABERT (6-mer) · Configuration · Author-reported evaluation55.50
- NT-500M-human · Configuration · Author-reported evaluation50.82
- NT-500M-1000g · Configuration · Author-reported evaluation52.06
- NT-2500M-1000g · Configuration · Author-reported evaluation66.73
- NT-2500M-multi · Configuration · Author-reported evaluation73.04
- DNABERT-2 · Configuration · Author-reported evaluation71.02
- DNABERT-2 (further pre-trained on GUE) · Configuration · Author-reported evaluation68.49
Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.
DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 12, row(Covid variant classification)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| DNABERT (3-mer) · Configuration | 62.23 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (3-mer)), column(Covid variant classification Covid) |
| DNABERT (4-mer) · Configuration | 59.87 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (4-mer)), column(Covid variant classification Covid) |
| DNABERT (5-mer) · Configuration | 50.46 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (5-mer)), column(Covid variant classification Covid) |
| DNABERT (6-mer) · Configuration | 55.50 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (6-mer)), column(Covid variant classification Covid) |
| NT-500M-human · Configuration | 50.82 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-human), column(Covid variant classification Covid) |
| NT-500M-1000g · Configuration | 52.06 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-1000g), column(Covid variant classification Covid) |
| NT-2500M-1000g · Configuration | 66.73 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-1000g), column(Covid variant classification Covid) |
| NT-2500M-multi · Configuration | 73.04 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-multi), column(Covid variant classification Covid) |
| DNABERT-2 · Configuration | 71.02 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2), column(Covid variant classification Covid) |
| DNABERT-2 (further pre-trained on GUE) · Configuration | 68.49 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2♦), column(Covid variant classification Covid) |
Scope and limitations
- Author-reported numbers, source checked but not independently reproduced.
- Scores are MCC, except Covid variant classification which is F1, both on a 0 to 100 scale.
- The diamond entry is DNABERT-2 with further pre-training on the GUE training sets, so it is not directly comparable to the others.
Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-134cd1815de8 · 10 evaluations · 10 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| DNABERT-2 on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: DNABERT-2Task: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 71.02% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| DNABERT-2 (further pre-trained on GUE) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: DNABERT-2 (further pre-trained on GUE)Task: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 68.49% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2♦), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| DNABERT (3-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: DNABERT (3-mer)Task: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 62.23% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (3-mer)), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| DNABERT (4-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: DNABERT (4-mer)Task: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 59.87% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (4-mer)), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| DNABERT (5-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: DNABERT (5-mer)Task: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 50.46% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (5-mer)), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| DNABERT (6-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: DNABERT (6-mer)Task: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 55.50% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (6-mer)), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| NT-2500M-1000g on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: NT-2500M-1000gTask: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 66.73% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-1000g), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| NT-2500M-multi on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: NT-2500M-multiTask: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 73.04% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-multi), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| NT-500M-1000g on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: NT-500M-1000gTask: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 52.06% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-1000g), column(Covid variant classification Covid) Source checking is not independent reproduction. |
| NT-500M-human on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid Configuration: NT-500M-humanTask: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset CovidDataset subset: GUE Covid variant classification, Covid (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 50.82% f1 Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-human), column(Covid variant classification Covid) Source checking is not independent reproduction. |
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-gue Individual claims | DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes Table 12, row(Covid variant classification) Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: gue-association-covid-variant-classification-covid Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Technical metadata and extraction receipts
Stable ID: gue-task-covid-variant-classification-covid
- areas
- dna-genomes
- tasks
- Covid variant classification, dataset Covid
- metric
- F1
- metric direction
- higher
- dataset
- GUE Covid variant classification, Covid
- protocol
- Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.
- source locator
- Table 12, row(Covid variant classification)
- comparison panels
- id: gue-panel-covid-variant-classification-covid; title: GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid; protocol id: gue-task-covid-variant-classification-covid; dataset id: gue-dataset-gue-covid-variant-classification-covid; metric: f1; unit: percent; direction: higher; result ids: gue-result-dnabert-3-mer-covid-variant-classification-covid-f1; gue-result-dnabert-4-mer-covid-variant-classification-covid-f1; gue-result-dnabert-5-mer-covid-variant-classification-covid-f1; gue-result-dnabert-6-mer-covid-variant-classification-covid-f1; gue-result-nt-500m-human-covid-variant-classification-covid-f1; gue-result-nt-500m-1000g-covid-variant-classification-covid-f1; gue-result-nt-2500m-1000g-covid-variant-classification-covid-f1; gue-result-nt-2500m-multi-covid-variant-classification-covid-f1; gue-result-dnabert-2-covid-variant-classification-covid-f1; gue-result-dnabert-2-further-pre-trained-on-gue-covid-variant-classification-covid-f1; source ids: evidence-expansion-gue-49300ace; source locator: Table 12, row(Covid variant classification); context: Every method GUE reports on Covid variant classification, dataset Covid, scored with F1 on GUE Covid variant classification, Covid.; caveats: Author-reported numbers, source checked but not independently reproduced.; Scores are MCC, except Covid variant classification which is F1, both on a 0 to 100 scale.; The diamond entry is DNABERT-2 with further pre-training on the GUE training sets, so it is not directly comparable to the others.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: GUE
- subject: GUE COVID-VARIANT-CLASSIFICATION-COVID: part of discovery-benchmark-gue
- benchmark: DNABERT-2 on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: DNABERT-2 (further pre-trained on GUE) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: DNABERT (3-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: DNABERT (4-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: DNABERT (5-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: DNABERT (6-mer) on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: NT-2500M-1000g on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: NT-2500M-multi on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: NT-500M-1000g on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid
- benchmark: NT-500M-human on GUE COVID-VARIANT-CLASSIFICATION-COVID: Covid variant classification, dataset Covid