NT benchmark normalised summed performance (Supplementary Table 9); Nature Methods 2025

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

23 recorded evaluations, 23 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

23 evaluations · 23 results. Different protocols are not a single leaderboard.

Protocol: NT benchmark normalised summed performance (Supplementary Table 9) · Dataset: NT benchmark, all 18 tasks

Sorted by MCC (mean over three task categories of median cross-validation MCC) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	MCC (mean over three task categories of median cross-validation MCC)
NT-Multispecies-v2 (250M), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.769 (best in column)
NT-Multispecies-v2 (500M), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.762
NT-Multispecies (2.5B), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.755
NT-Multispecies-v2 (100M), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.748
NT-1000G (2.5B), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.738
NT-HumanRef (500M), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.733
NT-Multispecies-v2 (50M), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.732
NT-1000G (500M), parameter-efficient fine-tuning (NT benchmark)Evaluation	0.729
DNABERT-2, parameter-efficient fine-tuning (NT benchmark)Evaluation	0.723
HyenaDNA-32KB, parameter-efficient fine-tuning (NT benchmark)Evaluation	0.691
Enformer, parameter-efficient fine-tuning (NT benchmark)Evaluation	0.684
BPNet (large), trained from scratch (NT benchmark)Evaluation	0.683
HyenaDNA-1KB, parameter-efficient fine-tuning (NT benchmark)Evaluation	0.668
BPNet (original), trained from scratch (NT benchmark)Evaluation	0.665
NT-Multispecies (2.5B), probing (NT benchmark)Evaluation	0.644
NT-1000G (2.5B), probing (NT benchmark)Evaluation	0.613
NT-1000G (500M), probing (NT benchmark)Evaluation	0.583
BPNet (X-large), trained from scratch (NT benchmark)Evaluation	0.566
NT-HumanRef (500M), probing (NT benchmark)Evaluation	0.534
DNABERT-1, fine-tuning (NT benchmark)Evaluation	0.511
NT 2.5B Randomly Initialized, trained from scratch (NT benchmark)Evaluation	0.399
Raw Probe, probing of raw sequence (NT benchmark)Evaluation	0.391
NT 500M Randomly Initialized, trained from scratch (NT benchmark)Evaluation	0.355

All 23 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: BPNet (large), trained from scratch (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.683 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BPNet (large) (control) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'BPNet (large)', approach 'control', column 'Average performance'
Configuration: BPNet (original), trained from scratch (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.665 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BPNet (original) (control) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'BPNet (original)', approach 'control', column 'Average performance'
Configuration: BPNet (X-large), trained from scratch (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.566 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BPNet (X-large) (control) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'BPNet (X-large)', approach 'control', column 'Average performance'
Configuration: DNABERT-1, fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.511 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-1 (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'DNABERT-1', approach 'Finetuning', column 'Average performance'
Configuration: DNABERT-2, parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.723 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2 (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'DNABERT-2', approach 'Finetuning', column 'Average performance'
Configuration: Enformer, parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.684 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enformer (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'Enformer', approach 'Finetuning', column 'Average performance'
Configuration: HyenaDNA-1KB, parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.668 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HyenaDNA-1KB (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'HyenaDNA-1KB', approach 'Finetuning', column 'Average performance'
Configuration: HyenaDNA-32KB, parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.691 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HyenaDNA-32KB (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'HyenaDNA-32KB', approach 'Finetuning', column 'Average performance'
Configuration: NT-1000G (2.5B), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.738 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-1000G (2.5B) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-1000G (2.5B)', approach 'Finetuning', column 'Average performance'
Configuration: NT-1000G (2.5B), probing (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.613 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-1000G (2.5B) (Probing) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-1000G (2.5B)', approach 'Probing', column 'Average performance'
Configuration: NT-1000G (500M), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.729 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-1000G (500M) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-1000G (500M)', approach 'Finetuning', column 'Average performance'
Configuration: NT-1000G (500M), probing (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.583 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-1000G (500M) (Probing) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-1000G (500M)', approach 'Probing', column 'Average performance'
Configuration: NT 2.5B Randomly Initialized, trained from scratch (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.399 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT 2.5B Randomly Initialized (Training from scratch) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT 2.5B Randomly Initialized', approach 'Training from scratch', column 'Average performance'
Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.355 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT 500M Randomly Initialized (Training from scratch) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT 500M Randomly Initialized', approach 'Training from scratch', column 'Average performance'
Configuration: NT-HumanRef (500M), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.733 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-HumanRef (500M) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-HumanRef (500M)', approach 'Finetuning', column 'Average performance'
Configuration: NT-HumanRef (500M), probing (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.534 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-HumanRef (500M) (Probing) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-HumanRef (500M)', approach 'Probing', column 'Average performance'
Configuration: NT-Multispecies (2.5B), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.755 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-Multispecies (2.5B) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-Multispecies (2.5B)', approach 'Finetuning', column 'Average performance'
Configuration: NT-Multispecies (2.5B), probing (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.644 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-Multispecies (2.5B) (Probing) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-Multispecies (2.5B)', approach 'Probing', column 'Average performance'
Configuration: NT-Multispecies-v2 (100M), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.748 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-Multispecies-v2 (100M) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-Multispecies-v2 (100M)', approach 'Finetuning', column 'Average performance'
Configuration: NT-Multispecies-v2 (250M), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.769 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-Multispecies-v2 (250M) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-Multispecies-v2 (250M)', approach 'Finetuning', column 'Average performance'
Configuration: NT-Multispecies-v2 (500M), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.762 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-Multispecies-v2 (500M) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-Multispecies-v2 (500M)', approach 'Finetuning', column 'Average performance'
Configuration: NT-Multispecies-v2 (50M), parameter-efficient fine-tuning (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.732 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-Multispecies-v2 (50M) (Finetuning) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT-Multispecies-v2 (50M)', approach 'Finetuning', column 'Average performance'
Configuration: Raw Probe, probing of raw sequence (NT benchmark)	Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks	0.391 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Raw Probe (Probing) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'Raw Probe', approach 'Probing', column 'Average performance'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 15
External evaluations: 8

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Evidence

Source checking verifies the cited claim or transcription. It does not establish 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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Original source · Nature Methods 22, 287-297 (published online 2024-11-28); Supplementary Information PDF (MOESM1, 25 pages)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-genomics-20261011-ntbench-protocol-normalised-summed-performance

areas: dna-genomes
contexts: research
protocol: Average of the median MCC obtained by each model on the three categories of downstream tasks (chromatin profiles, regulatory elements, splicing).
version: Nature Methods 2025
metric: matthews-correlation-coefficient
metric direction: higher
unit: unitless
limitations: Aggregate computed by the authors; per-category values are not printed in this table.
source locator: Supplementary Table 9

Related records

part of: Nucleotide Transformer benchmark (18 tasks)
uses data: NT benchmark, all 18 tasks
assessment: BPNet (large) (control) NT benchmark normalised summed performance
assessment: BPNet (original) (control) NT benchmark normalised summed performance
assessment: BPNet (X-large) (control) NT benchmark normalised summed performance
assessment: DNABERT-1 (Finetuning) NT benchmark normalised summed performance
assessment: DNABERT-2 (Finetuning) NT benchmark normalised summed performance
assessment: Enformer (Finetuning) NT benchmark normalised summed performance
assessment: HyenaDNA-1KB (Finetuning) NT benchmark normalised summed performance
assessment: HyenaDNA-32KB (Finetuning) NT benchmark normalised summed performance
assessment: NT-1000G (2.5B) (Finetuning) NT benchmark normalised summed performance
assessment: NT-1000G (2.5B) (Probing) NT benchmark normalised summed performance
assessment: NT-1000G (500M) (Finetuning) NT benchmark normalised summed performance
assessment: NT-1000G (500M) (Probing) NT benchmark normalised summed performance
assessment: NT 2.5B Randomly Initialized (Training from scratch) NT benchmark normalised summed performance
assessment: NT 500M Randomly Initialized (Training from scratch) NT benchmark normalised summed performance
assessment: NT-HumanRef (500M) (Finetuning) NT benchmark normalised summed performance
assessment: NT-HumanRef (500M) (Probing) NT benchmark normalised summed performance
assessment: NT-Multispecies (2.5B) (Finetuning) NT benchmark normalised summed performance
assessment: NT-Multispecies (2.5B) (Probing) NT benchmark normalised summed performance
assessment: NT-Multispecies-v2 (100M) (Finetuning) NT benchmark normalised summed performance
assessment: NT-Multispecies-v2 (250M) (Finetuning) NT benchmark normalised summed performance
assessment: NT-Multispecies-v2 (500M) (Finetuning) NT benchmark normalised summed performance
assessment: NT-Multispecies-v2 (50M) (Finetuning) NT benchmark normalised summed performance
assessment: Raw Probe (Probing) NT benchmark normalised summed performance