rewire.it
Benchmark

Genie 3 unconditional short monomer comparison

Bounded complete Table 3 comparison across 13 method/version rows. Five directional metrics are included; secondary-structure composition is retained separately without ranking.

13 evaluations · 65 metric rows

Overview

Bounded complete Table 3 comparison across 13 method/version rows. Five directional metrics are included; secondary-structure composition is retained separately without ranking.

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

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

Genie 3 short monomer generation designability: Unconditional short monomer Designability

designability (reported score) · Higher values are better.

Every method Genie 3 short monomer generation reports on Unconditional short monomer Designability, scored with Designability on 500 generated monomers per run; lengths 50–250 in steps of 50; three runs.

Genie 3 short monomer generation designability: Unconditional short monomer Designability · 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split)

Evidence origin: Author-reported evaluation. Numerical source review does not establish independent reproduction.

Genie 3 primary paper v1, Table 3 · Appendix B.1–B.3; Table 3, column Designability, PDF pages 18–20

Source-checked author-reported results, not independently reproduced. All 13 method/version rows are retained.

All comparison limitations (6)
  • Source-checked author-reported results, not independently reproduced. All 13 method/version rows are retained.
  • The five metrics are separate; no cross-metric aggregate is defined. Original fractional-scale printed values are preserved without rescaling.
  • Table 3 reports averages across three runs, not confidence intervals. Per-run tables 4 and 5 are retained in the source but are not extra independent evidence.
  • Diversity is reported on the table’s fractional scale; Appendix B.1 describes cluster counts but does not explicitly state the displayed normalization. Exact original values are preserved.
  • Novelty is mean one minus maximum structural similarity among designable structures; unmatched exhaustive-search cases receive novelty 1 in the source procedure.
  • The alpha/beta secondary-structure percentages are retained in the 91-cell source receipt as descriptive metadata and excluded from directional rankings.

Automated source review: 2026-09-23.

No unavailable values; missing scores remain labelled and are never plotted as zero.

Showing 12 of 13 matching rows.

Tested configuration
0.820.8670.9150.9631.01
Reported score
  1. Protpardelle-1c (cc58)1.00
  2. La-Proteina (LD1)0.99
  3. La-Proteina (LD2)0.99
  4. FoldFlow 2 (base)0.97
  5. Protpardelle-1c (cc94)0.97
  6. Ambient (short)0.97
  7. Genie 30.97
  8. Genie 20.94
  9. RFDiffusion0.93
  10. Proteus0.93
  11. Proteina (MFS)0.92
  12. FrameFlow0.90

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Protocols

These source-backed links do not make different protocols or scores interchangeable.

Baseline coverage

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

0 of 10 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

Baseline status by linked protocol

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

Coverage is derived from release 2026-09-23-2b89723c6dd9. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run this benchmark

Choose a concrete protocol before running an evaluation. Its inputs, split and scoring rules determine which results can be compared.

Run instructions

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

Strengths, limitations and unresolved questions

Evidence

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

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-23-2b89723c6dd9
Property and statementOriginal source and locationReview and provenance

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

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-23-2b89723c6dd9 · Record review: source checked

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

Stable ID: model-coverage-genie3-short-monomers

areas
proteins-complexes
entity level
suite
source locator
Appendix B.1–B.3, Table 3, PDF pages 18–20
missing metadata
runner: unavailable; split manifest: unextracted
Related records

Suggest a correction