rewire.it
Task

NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC. Scored with Zero-shot AUC on NABench deep mutational scanning assays. Aggregated by the NABench authors across NABench deep mutational scanning assays.

25 evaluations · 25 metric rows

Overview

Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC. Scored with Zero-shot AUC on NABench deep mutational scanning assays. Aggregated by the NABench authors across NABench deep mutational scanning 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 DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

auc (fraction) · Higher values are better for this metric.

Every method NABench reports on Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC, scored with Zero-shot AUC on NABench deep mutational scanning assays.

Evaluation protocol · NABench deep mutational scanning assays (NABench split)

  1. RNA-FM · Configuration · Author-reported evaluation0.541
  2. RNAernie · Configuration · Author-reported evaluation0.481
  3. SPACE · Configuration · Author-reported evaluation0.519
  4. AIDO.RNA · Configuration · Author-reported evaluation0.472
  5. BiRNA-BERT · Configuration · Author-reported evaluation0.518
  6. Crafts · Configuration · Author-reported evaluation0.488
  7. Dnabert · Configuration · Author-reported evaluation0.539
  8. Dnabert_6 · Configuration · Author-reported evaluation0.482
  9. Enformer · Configuration · Author-reported evaluation0.499
  10. Evo2-7B · Configuration · Author-reported evaluation0.541
  11. Evo2-7B-base · Configuration · Author-reported evaluation0.547
  12. Evo_1.5_8k_base · Configuration · Author-reported evaluation0.543
  13. Evo_1_8k · Configuration · Author-reported evaluation0.542
  14. Evo_1_8k_base · Configuration · Author-reported evaluation0.542
  15. GENA-LM-large · Configuration · Author-reported evaluation0.529
  16. GENERator-3B · Configuration · Author-reported evaluation0.499
  17. GenerRNA · Configuration · Author-reported evaluation0.493
  18. GenSLM · Configuration · Author-reported evaluation0.482
  19. HyenaDNA · Configuration · Author-reported evaluation0.483
  20. LucaOne · Configuration · Author-reported evaluation0.486
  21. LucaVirus · Configuration · Author-reported evaluation0.467
  22. N.T.-v2-50m · Configuration · Author-reported evaluation0.512
  23. RESM · Configuration · Author-reported evaluation0.557
  24. RiNALMo_giga · Configuration · Author-reported evaluation0.488
  25. structRFM · Configuration · Author-reported evaluation0.469

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 6, column(Zero-shot AUC)
Values, uncertainty and evidence
auc: original source values
Tested entityPrinted valueUncertaintyEvidence
RNA-FM · Configuration0.541 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RNA-FM), column(Zero-shot AUC)
RNAernie · Configuration0.481 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RNAernie), column(Zero-shot AUC)
SPACE · Configuration0.519 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(SPACE), column(Zero-shot AUC)
AIDO.RNA · Configuration0.472 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(AIDO.RNA), column(Zero-shot AUC)
BiRNA-BERT · Configuration0.518 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(BiRNA-BERT), column(Zero-shot AUC)
Crafts · Configuration0.488 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Crafts), column(Zero-shot AUC)
Dnabert · Configuration0.539 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Dnabert), column(Zero-shot AUC)
Dnabert_6 · Configuration0.482 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Dnabert_6), column(Zero-shot AUC)
Enformer · Configuration0.499 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Enformer), column(Zero-shot AUC)
Evo2-7B · Configuration0.541 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo2-7B), column(Zero-shot AUC)
Evo2-7B-base · Configuration0.547 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo2-7B-base), column(Zero-shot AUC)
Evo_1.5_8k_base · Configuration0.543 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1.5_8k_base), column(Zero-shot AUC)
Evo_1_8k · Configuration0.542 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1_8k), column(Zero-shot AUC)
Evo_1_8k_base · Configuration0.542 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1_8k_base), column(Zero-shot AUC)
GENA-LM-large · Configuration0.529 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GENA-LM-large), column(Zero-shot AUC)
GENERator-3B · Configuration0.499 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GENERator-3B), column(Zero-shot AUC)
GenerRNA · Configuration0.493 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GenerRNA), column(Zero-shot AUC)
GenSLM · Configuration0.482 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GenSlm), column(Zero-shot AUC)
HyenaDNA · Configuration0.483 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(HyenaDNA), column(Zero-shot AUC)
LucaOne · Configuration0.486 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(LucaOne), column(Zero-shot AUC)
LucaVirus · Configuration0.467 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(LucaVirus), column(Zero-shot AUC)
N.T.-v2-50m · Configuration0.512 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(N.T.-v2-50m), column(Zero-shot AUC)
RESM · Configuration0.557 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RESM), column(Zero-shot AUC)
RiNALMo_giga · Configuration0.488 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RiNALMo_giga), column(Zero-shot AUC)
structRFM · Configuration0.469 fractionNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(structRFM), column(Zero-shot AUC)
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 DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.472 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(AIDO.RNA), column(Zero-shot AUC)

Source checking is not independent reproduction.

BiRNA-BERT on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.518 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(BiRNA-BERT), column(Zero-shot AUC)

Source checking is not independent reproduction.

Crafts on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.488 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Crafts), column(Zero-shot AUC)

Source checking is not independent reproduction.

Dnabert_6 on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.482 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Dnabert_6), column(Zero-shot AUC)

Source checking is not independent reproduction.

Dnabert on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.539 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Dnabert), column(Zero-shot AUC)

Source checking is not independent reproduction.

Enformer on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.499 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Enformer), column(Zero-shot AUC)

Source checking is not independent reproduction.

Evo_1.5_8k_base on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.543 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1.5_8k_base), column(Zero-shot AUC)

Source checking is not independent reproduction.

Evo_1_8k_base on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.542 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1_8k_base), column(Zero-shot AUC)

Source checking is not independent reproduction.

Evo_1_8k on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.542 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1_8k), column(Zero-shot AUC)

Source checking is not independent reproduction.

Evo2-7B-base on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.547 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo2-7B-base), column(Zero-shot AUC)

Source checking is not independent reproduction.

Evo2-7B on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.541 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo2-7B), column(Zero-shot AUC)

Source checking is not independent reproduction.

GENA-LM-large on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.529 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GENA-LM-large), column(Zero-shot AUC)

Source checking is not independent reproduction.

GENERator-3B on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.499 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GENERator-3B), column(Zero-shot AUC)

Source checking is not independent reproduction.

GenerRNA on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.493 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GenerRNA), column(Zero-shot AUC)

Source checking is not independent reproduction.

GenSLM on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.482 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GenSlm), column(Zero-shot AUC)

Source checking is not independent reproduction.

HyenaDNA on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.483 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(HyenaDNA), column(Zero-shot AUC)

Source checking is not independent reproduction.

LucaOne on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.486 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(LucaOne), column(Zero-shot AUC)

Source checking is not independent reproduction.

LucaVirus on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.467 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(LucaVirus), column(Zero-shot AUC)

Source checking is not independent reproduction.

N.T.-v2-50m on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.512 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(N.T.-v2-50m), column(Zero-shot AUC)

Source checking is not independent reproduction.

RESM on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.557 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RESM), column(Zero-shot AUC)

Source checking is not independent reproduction.

RiNALMo_giga on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.488 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RiNALMo_giga), column(Zero-shot AUC)

Source checking is not independent reproduction.

RNA-FM on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.541 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RNA-FM), column(Zero-shot AUC)

Source checking is not independent reproduction.

RNAernie on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.481 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RNAernie), column(Zero-shot AUC)

Source checking is not independent reproduction.

SPACE on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.519 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(SPACE), column(Zero-shot AUC)

Source checking is not independent reproduction.

structRFM on NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC

Aggregated by the NABench authors across NABench deep mutational scanning assays.

Author-reported evaluation · Evaluation metadata: source checked

0.469 auc

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(structRFM), column(Zero-shot AUC)

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 6, column(Zero-shot AUC)

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-dms-zs-auc

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-dms-zs-auc

areas
rna-transcriptomes
tasks
Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC
metric
Zero-shot AUC
metric direction
higher
dataset
NABench deep mutational scanning assays
protocol
Aggregated by the NABench authors across NABench deep mutational scanning assays.
source locator
Table 6, column(Zero-shot AUC)
comparison panels
id: nabench-panel-dms-zs-auc; title: NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC; protocol id: nabench-task-dms-zs-auc; dataset id: nabench-dataset-nabench-deep-mutational-scanning-assays; metric: auc; unit: fraction; direction: higher; result ids: nabench-result-rna-fm-dms-zs-auc-auc; nabench-result-rnaernie-dms-zs-auc-auc; nabench-result-space-dms-zs-auc-auc; nabench-result-aido-rna-dms-zs-auc-auc; nabench-result-birna-bert-dms-zs-auc-auc; nabench-result-crafts-dms-zs-auc-auc; nabench-result-dnabert-dms-zs-auc-auc; nabench-result-dnabert-6-dms-zs-auc-auc; nabench-result-enformer-dms-zs-auc-auc; nabench-result-evo2-7b-dms-zs-auc-auc; nabench-result-evo2-7b-base-dms-zs-auc-auc; nabench-result-evo-1-5-8k-base-dms-zs-auc-auc; nabench-result-evo-1-8k-dms-zs-auc-auc; nabench-result-evo-1-8k-base-dms-zs-auc-auc; nabench-result-gena-lm-large-dms-zs-auc-auc; nabench-result-generator-3b-dms-zs-auc-auc; nabench-result-generrna-dms-zs-auc-auc; nabench-result-genslm-dms-zs-auc-auc; nabench-result-hyenadna-dms-zs-auc-auc; nabench-result-lucaone-dms-zs-auc-auc; nabench-result-lucavirus-dms-zs-auc-auc; nabench-result-n-t-v2-50m-dms-zs-auc-auc; nabench-result-resm-dms-zs-auc-auc; nabench-result-rinalmo-giga-dms-zs-auc-auc; nabench-result-structrfm-dms-zs-auc-auc; source ids: evidence-expansion-nabench-fefd48d5; source locator: Table 6, column(Zero-shot AUC); context: Every method NABench reports on Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC, scored with Zero-shot AUC on NABench deep mutational scanning 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