rewire.it
Task

NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ. Scored with Random cross validation Spearman ρ on NABench SELEX assays. Aggregated by the NABench authors across NABench SELEX assays.

25 evaluations · 25 metric rows

Overview

Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ. Scored with Random cross validation Spearman ρ on NABench SELEX assays. Aggregated by the NABench authors across NABench SELEX assays.

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.

Explore all linked results

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.

NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

spearman (correlation) · Higher values are better for this metric.

Every method NABench reports on Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ, scored with Random cross validation Spearman ρ on NABench SELEX assays.

Evaluation protocol · NABench SELEX assays (NABench split)

  1. RNA-FM · Configuration · Author-reported evaluation0.685
  2. RNAernie · Configuration · Author-reported evaluation0.637
  3. SPACE · Configuration · Author-reported evaluation0.608
  4. AIDO.RNA · Configuration · Author-reported evaluation0.687
  5. BiRNA-BERT · Configuration · Author-reported evaluation0.681
  6. Crafts · Configuration · Author-reported evaluation0.654
  7. Dnabert · Configuration · Author-reported evaluation0.669
  8. Dnabert_6 · Configuration · Author-reported evaluation0.606
  9. Enformer · Configuration · Author-reported evaluation0.574
  10. Evo2-7B · Configuration · Author-reported evaluation0.597
  11. Evo2-7B-base · Configuration · Author-reported evaluation0.596
  12. Evo_1.5_8k_base · Configuration · Author-reported evaluation0.635
  13. Evo_1_8k · Configuration · Author-reported evaluation0.738
  14. Evo_1_8k_base · Configuration · Author-reported evaluation0.691
  15. GENA-LM-large · Configuration · Author-reported evaluation0.627
  16. GENERator-3B · Configuration · Author-reported evaluation0.657
  17. GenerRNA · Configuration · Author-reported evaluation0.642
  18. GenSLM · Configuration · Author-reported evaluation0.631
  19. HyenaDNA · Configuration · Author-reported evaluation0.656
  20. LucaOne · Configuration · Author-reported evaluation0.695
  21. LucaVirus · Configuration · Author-reported evaluation0.693
  22. N.T.-v2-500m · Configuration · Author-reported evaluation0.626
  23. N.T.-v2-50m · Configuration · Author-reported evaluation0.66
  24. RESM · Configuration · Author-reported evaluation0.681
  25. RiNALMo_giga · Configuration · Author-reported evaluation0.665

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.

NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, column(Random cross validation Spearman ρ)
Values, uncertainty and evidence
spearman: original source values
Tested entityPrinted valueUncertaintyEvidence
RNA-FM · Configuration0.685 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RNA-FM), column(Random cross validation Spearman ρ)
RNAernie · Configuration0.637 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RNAernie), column(Random cross validation Spearman ρ)
SPACE · Configuration0.608 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(SPACE), column(Random cross validation Spearman ρ)
AIDO.RNA · Configuration0.687 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(AIDO.RNA), column(Random cross validation Spearman ρ)
BiRNA-BERT · Configuration0.681 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(BiRNA-BERT), column(Random cross validation Spearman ρ)
Crafts · Configuration0.654 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Crafts), column(Random cross validation Spearman ρ)
Dnabert · Configuration0.669 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Dnabert), column(Random cross validation Spearman ρ)
Dnabert_6 · Configuration0.606 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Dnabert_6), column(Random cross validation Spearman ρ)
Enformer · Configuration0.574 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Enformer), column(Random cross validation Spearman ρ)
Evo2-7B · Configuration0.597 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo2-7B), column(Random cross validation Spearman ρ)
Evo2-7B-base · Configuration0.596 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo2-7B-base), column(Random cross validation Spearman ρ)
Evo_1.5_8k_base · Configuration0.635 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo_1.5_8k_base), column(Random cross validation Spearman ρ)
Evo_1_8k · Configuration0.738 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo_1_8k), column(Random cross validation Spearman ρ)
Evo_1_8k_base · Configuration0.691 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo_1_8k_base), column(Random cross validation Spearman ρ)
GENA-LM-large · Configuration0.627 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GENA-LM-large), column(Random cross validation Spearman ρ)
GENERator-3B · Configuration0.657 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GENERator-3B), column(Random cross validation Spearman ρ)
GenerRNA · Configuration0.642 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GenerRNA), column(Random cross validation Spearman ρ)
GenSLM · Configuration0.631 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GenSLM), column(Random cross validation Spearman ρ)
HyenaDNA · Configuration0.656 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(HyenaDNA), column(Random cross validation Spearman ρ)
LucaOne · Configuration0.695 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(LucaOne), column(Random cross validation Spearman ρ)
LucaVirus · Configuration0.693 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(LucaVirus), column(Random cross validation Spearman ρ)
N.T.-v2-500m · Configuration0.626 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(N.T.-v2-500m), column(Random cross validation Spearman ρ)
N.T.-v2-50m · Configuration0.66 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(N.T.-v2-50m), column(Random cross validation Spearman ρ)
RESM · Configuration0.681 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RESM), column(Random cross validation Spearman ρ)
RiNALMo_giga · Configuration0.665 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RiNALMo_giga), column(Random cross validation Spearman ρ)
Scope and limitations
  • Author-reported numbers, source checked but not independently reproduced.
  • Zero-shot, few-shot and supervised cross validation figures come from different protocols and are not comparable to each other.
  • The per-nucleotide-type figures and the overall figures describe the same runs at different resolutions, so they must not be combined.

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 · 25 evaluations · 25 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.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
AIDO.RNA on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.687 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(AIDO.RNA), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

BiRNA-BERT on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.681 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(BiRNA-BERT), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Crafts on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.654 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Crafts), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Dnabert_6 on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.606 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Dnabert_6), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Dnabert on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.669 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Dnabert), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Enformer on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.574 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Enformer), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Evo_1.5_8k_base on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.635 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo_1.5_8k_base), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Evo_1_8k_base on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.691 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo_1_8k_base), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Evo_1_8k on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.738 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo_1_8k), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Evo2-7B-base on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.596 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo2-7B-base), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

Evo2-7B on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.597 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(Evo2-7B), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

GENA-LM-large on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.627 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GENA-LM-large), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

GENERator-3B on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.657 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GENERator-3B), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

GenerRNA on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.642 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GenerRNA), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

GenSLM on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.631 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(GenSLM), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

HyenaDNA on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.656 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(HyenaDNA), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

LucaOne on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.695 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(LucaOne), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

LucaVirus on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.693 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(LucaVirus), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

N.T.-v2-500m on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.626 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(N.T.-v2-500m), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

N.T.-v2-50m on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.66 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(N.T.-v2-50m), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

RESM on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.681 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RESM), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

RiNALMo_giga on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.665 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RiNALMo_giga), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

RNA-FM on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.685 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RNA-FM), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

RNAernie on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.637 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(RNAernie), column(Random cross validation Spearman ρ)

Source checking is not independent reproduction.

SPACE on NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ

Aggregated by the NABench authors across NABench SELEX assays.

Author-reported evaluation · Evaluation metadata: source checked

0.608 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 12, row(SPACE), column(Random cross validation Spearman ρ)

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

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-nabench

Individual claims
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction

Original source ↗

Table 12, column(Random cross validation Spearman ρ)

Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Retrieved: 2026-09-17T08:06:28.183421+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-nabench

Claim: nabench-association-selex-rcv

Source artifact SHA-256: fefd48d53b1a7eadf9e14db96adacc8e646304c1b592562d9f136f4508941350

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: nabench-task-selex-rcv

areas
rna-transcriptomes
tasks
Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ
metric
Random cross validation Spearman ρ
metric direction
higher
dataset
NABench SELEX assays
protocol
Aggregated by the NABench authors across NABench SELEX assays.
source locator
Table 12, column(Random cross validation Spearman ρ)
comparison panels
id: nabench-panel-selex-rcv; title: NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ; protocol id: nabench-task-selex-rcv; dataset id: nabench-dataset-nabench-selex-assays; metric: spearman; unit: correlation; direction: higher; result ids: nabench-result-rna-fm-selex-rcv-spearman; nabench-result-rnaernie-selex-rcv-spearman; nabench-result-space-selex-rcv-spearman; nabench-result-aido-rna-selex-rcv-spearman; nabench-result-birna-bert-selex-rcv-spearman; nabench-result-crafts-selex-rcv-spearman; nabench-result-dnabert-selex-rcv-spearman; nabench-result-dnabert-6-selex-rcv-spearman; nabench-result-enformer-selex-rcv-spearman; nabench-result-evo2-7b-selex-rcv-spearman; nabench-result-evo2-7b-base-selex-rcv-spearman; nabench-result-evo-1-5-8k-base-selex-rcv-spearman; nabench-result-evo-1-8k-selex-rcv-spearman; nabench-result-evo-1-8k-base-selex-rcv-spearman; nabench-result-gena-lm-large-selex-rcv-spearman; nabench-result-generator-3b-selex-rcv-spearman; nabench-result-generrna-selex-rcv-spearman; nabench-result-genslm-selex-rcv-spearman; nabench-result-hyenadna-selex-rcv-spearman; nabench-result-lucaone-selex-rcv-spearman; nabench-result-lucavirus-selex-rcv-spearman; nabench-result-n-t-v2-500m-selex-rcv-spearman; nabench-result-n-t-v2-50m-selex-rcv-spearman; nabench-result-resm-selex-rcv-spearman; nabench-result-rinalmo-giga-selex-rcv-spearman; source ids: evidence-expansion-nabench-fefd48d5; source locator: Table 12, column(Random cross validation Spearman ρ); context: Every method NABench reports on Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ, scored with Random cross validation Spearman ρ on NABench SELEX assays.; caveats: Author-reported numbers, source checked but not independently reproduced.; Zero-shot, few-shot and supervised cross validation figures come from different protocols and are not comparable to each other.; The per-nucleotide-type figures and the overall figures describe the same runs at different resolutions, so they must not be combined.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction