NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG. Scored with Zero-shot NDCG on NABench deep mutational scanning assays. Aggregated by the NABench authors across NABench deep mutational scanning assays.
Overview
Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG. Scored with Zero-shot NDCG 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.
- AIDO.RNA on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- BiRNA-BERT on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Crafts on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Dnabert_6 on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Dnabert on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Enformer on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Evo_1.5_8k_base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Evo_1_8k_base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Evo_1_8k on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Evo2-7B-base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- Evo2-7B on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- GENA-LM-large on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
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-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
ndcg (fraction) · Higher values are better for this metric.
Every method NABench reports on Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG, scored with Zero-shot NDCG on NABench deep mutational scanning assays.
Evaluation protocol · NABench deep mutational scanning assays (NABench split)
- RNA-FM · Configuration · Author-reported evaluation0.380
- RNAernie · Configuration · Author-reported evaluation0.353
- SPACE · Configuration · Author-reported evaluation0.349
- AIDO.RNA · Configuration · Author-reported evaluation0.324
- BiRNA-BERT · Configuration · Author-reported evaluation0.369
- Crafts · Configuration · Author-reported evaluation0.322
- Dnabert · Configuration · Author-reported evaluation0.370
- Dnabert_6 · Configuration · Author-reported evaluation0.343
- Enformer · Configuration · Author-reported evaluation0.344
- Evo2-7B · Configuration · Author-reported evaluation0.402
- Evo2-7B-base · Configuration · Author-reported evaluation0.410
- Evo_1.5_8k_base · Configuration · Author-reported evaluation0.396
- Evo_1_8k · Configuration · Author-reported evaluation0.389
- Evo_1_8k_base · Configuration · Author-reported evaluation0.389
- GENA-LM-large · Configuration · Author-reported evaluation0.364
- GENERator-3B · Configuration · Author-reported evaluation0.349
- GenerRNA · Configuration · Author-reported evaluation0.357
- GenSLM · Configuration · Author-reported evaluation0.331
- HyenaDNA · Configuration · Author-reported evaluation0.334
- LucaOne · Configuration · Author-reported evaluation0.349
- LucaVirus · Configuration · Author-reported evaluation0.343
- N.T.-v2-50m · Configuration · Author-reported evaluation0.349
- RESM · Configuration · Author-reported evaluation0.408
- RiNALMo_giga · Configuration · Author-reported evaluation0.338
- structRFM · Configuration · Author-reported evaluation0.327
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 NDCG)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| RNA-FM · Configuration | 0.380 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RNA-FM), column(Zero-shot NDCG) |
| RNAernie · Configuration | 0.353 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RNAernie), column(Zero-shot NDCG) |
| SPACE · Configuration | 0.349 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(SPACE), column(Zero-shot NDCG) |
| AIDO.RNA · Configuration | 0.324 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(AIDO.RNA), column(Zero-shot NDCG) |
| BiRNA-BERT · Configuration | 0.369 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(BiRNA-BERT), column(Zero-shot NDCG) |
| Crafts · Configuration | 0.322 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Crafts), column(Zero-shot NDCG) |
| Dnabert · Configuration | 0.370 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Dnabert), column(Zero-shot NDCG) |
| Dnabert_6 · Configuration | 0.343 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Dnabert_6), column(Zero-shot NDCG) |
| Enformer · Configuration | 0.344 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Enformer), column(Zero-shot NDCG) |
| Evo2-7B · Configuration | 0.402 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo2-7B), column(Zero-shot NDCG) |
| Evo2-7B-base · Configuration | 0.410 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo2-7B-base), column(Zero-shot NDCG) |
| Evo_1.5_8k_base · Configuration | 0.396 fraction | Not reported | Author-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 NDCG) |
| Evo_1_8k · Configuration | 0.389 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1_8k), column(Zero-shot NDCG) |
| Evo_1_8k_base · Configuration | 0.389 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(Evo_1_8k_base), column(Zero-shot NDCG) |
| GENA-LM-large · Configuration | 0.364 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GENA-LM-large), column(Zero-shot NDCG) |
| GENERator-3B · Configuration | 0.349 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GENERator-3B), column(Zero-shot NDCG) |
| GenerRNA · Configuration | 0.357 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GenerRNA), column(Zero-shot NDCG) |
| GenSLM · Configuration | 0.331 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(GenSlm), column(Zero-shot NDCG) |
| HyenaDNA · Configuration | 0.334 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(HyenaDNA), column(Zero-shot NDCG) |
| LucaOne · Configuration | 0.349 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(LucaOne), column(Zero-shot NDCG) |
| LucaVirus · Configuration | 0.343 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(LucaVirus), column(Zero-shot NDCG) |
| N.T.-v2-50m · Configuration | 0.349 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(N.T.-v2-50m), column(Zero-shot NDCG) |
| RESM · Configuration | 0.408 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RESM), column(Zero-shot NDCG) |
| RiNALMo_giga · Configuration | 0.338 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(RiNALMo_giga), column(Zero-shot NDCG) |
| structRFM · Configuration | 0.327 fraction | Not reported | Author-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 6, row(structRFM), column(Zero-shot NDCG) |
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.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| AIDO.RNA on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: AIDO.RNATask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.324 ndcg 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 NDCG) Source checking is not independent reproduction. |
| BiRNA-BERT on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: BiRNA-BERTTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.369 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Crafts on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: CraftsTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.322 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Dnabert_6 on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: Dnabert_6Task: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.343 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Dnabert on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: DnabertTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.370 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Enformer on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: EnformerTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.344 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Evo_1.5_8k_base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: Evo_1.5_8k_baseTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.396 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Evo_1_8k_base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: Evo_1_8k_baseTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.389 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Evo_1_8k on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: Evo_1_8kTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.389 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Evo2-7B-base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: Evo2-7B-baseTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.410 ndcg 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 NDCG) Source checking is not independent reproduction. |
| Evo2-7B on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: Evo2-7BTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.402 ndcg 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 NDCG) Source checking is not independent reproduction. |
| GENA-LM-large on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: GENA-LM-largeTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.364 ndcg 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 NDCG) Source checking is not independent reproduction. |
| GENERator-3B on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: GENERator-3BTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.349 ndcg 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 NDCG) Source checking is not independent reproduction. |
| GenerRNA on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: GenerRNATask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.357 ndcg 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 NDCG) Source checking is not independent reproduction. |
| GenSLM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: GenSLMTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.331 ndcg 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 NDCG) Source checking is not independent reproduction. |
| HyenaDNA on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: HyenaDNATask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.334 ndcg 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 NDCG) Source checking is not independent reproduction. |
| LucaOne on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: LucaOneTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.349 ndcg 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 NDCG) Source checking is not independent reproduction. |
| LucaVirus on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: LucaVirusTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.343 ndcg 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 NDCG) Source checking is not independent reproduction. |
| N.T.-v2-50m on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: N.T.-v2-50mTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.349 ndcg 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 NDCG) Source checking is not independent reproduction. |
| RESM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: RESMTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.408 ndcg 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 NDCG) Source checking is not independent reproduction. |
| RiNALMo_giga on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: RiNALMo_gigaTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.338 ndcg 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 NDCG) Source checking is not independent reproduction. |
| RNA-FM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: RNA-FMTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.380 ndcg 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 NDCG) Source checking is not independent reproduction. |
| RNAernie on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: RNAernieTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.353 ndcg 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 NDCG) Source checking is not independent reproduction. |
| SPACE on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: SPACETask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.349 ndcg 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 NDCG) Source checking is not independent reproduction. |
| structRFM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG Configuration: structRFMTask: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCGDataset subset: NABench deep mutational scanning assays (NABench split) Aggregated by the NABench authors across NABench deep mutational scanning assays. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.327 ndcg 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 NDCG) 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-nabench Individual claims | NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction Table 6, column(Zero-shot NDCG) 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: nabench-association-dms-zs-ndcg 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
- NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Technical metadata and extraction receipts
Stable ID: nabench-task-dms-zs-ndcg
- areas
- rna-transcriptomes
- tasks
- Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- metric
- Zero-shot NDCG
- 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 NDCG)
- comparison panels
- id: nabench-panel-dms-zs-ndcg; title: NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG; protocol id: nabench-task-dms-zs-ndcg; dataset id: nabench-dataset-nabench-deep-mutational-scanning-assays; metric: ndcg; unit: fraction; direction: higher; result ids: nabench-result-rna-fm-dms-zs-ndcg-ndcg; nabench-result-rnaernie-dms-zs-ndcg-ndcg; nabench-result-space-dms-zs-ndcg-ndcg; nabench-result-aido-rna-dms-zs-ndcg-ndcg; nabench-result-birna-bert-dms-zs-ndcg-ndcg; nabench-result-crafts-dms-zs-ndcg-ndcg; nabench-result-dnabert-dms-zs-ndcg-ndcg; nabench-result-dnabert-6-dms-zs-ndcg-ndcg; nabench-result-enformer-dms-zs-ndcg-ndcg; nabench-result-evo2-7b-dms-zs-ndcg-ndcg; nabench-result-evo2-7b-base-dms-zs-ndcg-ndcg; nabench-result-evo-1-5-8k-base-dms-zs-ndcg-ndcg; nabench-result-evo-1-8k-dms-zs-ndcg-ndcg; nabench-result-evo-1-8k-base-dms-zs-ndcg-ndcg; nabench-result-gena-lm-large-dms-zs-ndcg-ndcg; nabench-result-generator-3b-dms-zs-ndcg-ndcg; nabench-result-generrna-dms-zs-ndcg-ndcg; nabench-result-genslm-dms-zs-ndcg-ndcg; nabench-result-hyenadna-dms-zs-ndcg-ndcg; nabench-result-lucaone-dms-zs-ndcg-ndcg; nabench-result-lucavirus-dms-zs-ndcg-ndcg; nabench-result-n-t-v2-50m-dms-zs-ndcg-ndcg; nabench-result-resm-dms-zs-ndcg-ndcg; nabench-result-rinalmo-giga-dms-zs-ndcg-ndcg; nabench-result-structrfm-dms-zs-ndcg-ndcg; source ids: evidence-expansion-nabench-fefd48d5; source locator: Table 6, column(Zero-shot NDCG); context: Every method NABench reports on Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG, scored with Zero-shot NDCG 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
- part of: NABench
- subject: NABench DMS-ZS-NDCG: part of discovery-benchmark-nabench
- benchmark: AIDO.RNA on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: BiRNA-BERT on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Crafts on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Dnabert_6 on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Dnabert on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Enformer on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Evo_1.5_8k_base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Evo_1_8k_base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Evo_1_8k on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Evo2-7B-base on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: Evo2-7B on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: GENA-LM-large on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: GENERator-3B on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: GenerRNA on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: GenSLM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: HyenaDNA on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: LucaOne on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: LucaVirus on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: N.T.-v2-50m on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: RESM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: RiNALMo_giga on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: RNA-FM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: RNAernie on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: SPACE on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG
- benchmark: structRFM on NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG