rewirebio.iobenchmarks
Evaluation

Evo 2 7B scoring throughput on Runpod L40S

Throughput of workload W1 on Runpod L40S: 5219 sequences of 8,192 bp for 3,893 variants at batch size 1.

Evaluation results

1 evaluation · 1 result. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Evo 2 7B zero-shot likelihood score on Runpod L40SProtocol: Evo 2 7B BRCA1 variant scoring throughput on one GPU (evo2-cloud-operations W1)
Dataset subset: BRCA1 saturation genome editing SNVs, all SNVs (evo2-cloud-operations W1)
0.612 Inference throughput
sample-per-second · higher

Uncertainty: Not reported by the source: The file gives no interval at this pointer.

Coverage: Not reported scored / Not reported eligible

Rewire evaluation · Source checked
Methods, coverage and source

Evo 2 7B scoring throughput on Runpod L40S

Workload W1, batch size 1

Aggregation: Not reported

evo2-cloud-operations recorded run b75c67aa: run receipt, Runpod L40S (P5, attempt-2); evo2-cloud-operations reproduction run 30e7ae49: run receipt, Runpod L40S (P5, attempt-1); evo2-cloud-operations: run log · evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1/sequences_per_second

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-11-21-c8bea25e5abb · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

Workload W1, batch size 1

Configuration
Evo 2 7B zero-shot likelihood score on Runpod L40S
Protocol
Evo 2 7B BRCA1 variant scoring throughput on one GPU (evo2-cloud-operations W1)
Dataset subset
BRCA1 saturation genome editing SNVs, all SNVs (evo2-cloud-operations W1)
origin
Rewire evaluation
configuration
f8ae11c9a1c45505487c978b4cb7e064c4e59905
protocol id
rewire-local-20261121-evo2ops-protocol-brca1-scoring-throughput
dataset version
rewire-local-20261121-evo2ops-dataset-brca1-all
split
none; every variant of the subset is scored
population
3893/3893
inputs
variant and reference sequence, or the lookup score for the variant
adaptation
zero-shot inference
metric implementation
src/evo2ops/workloads.py; the recorded run used revision e93491a (evidence/runs/recorded-b75c67aa/provenance.json), an ancestor of the pinned commit
aggregation
sequences scored divided by scoring seconds, one run
budget
one run per platform

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split
none; every variant of the subset is scored
Adaptation
zero-shot inference
Scoring implementation
src/evo2ops/workloads.py; the recorded run used revision e93491a (evidence/runs/recorded-b75c67aa/provenance.json), an ancestor of the pinned commit

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

84 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Comparison: adaptation
zero-shot inference
Context-only references
evo2-cloud-operations reproduction run 30e7ae49: run receipt, Runpod L40S (P5, attempt-1)

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 60f60324a7cda6b66b370ea2569e71175f66a1baf64455d17b6a65813df02fd8

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: adaptation
zero-shot inference
Context-only references
evo2-cloud-operations recorded run b75c67aa: run receipt, Runpod L40S (P5, attempt-2)

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: d26432852833b76a63d4b91024cbe2c7a07a670dd5bbbcca2977f2139975a1eb

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: adaptation
zero-shot inference
Context-only references
evo2-cloud-operations: run log

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 9b42944eb2c1c7afeeb295f725bf1945ad8470f355b6a2e21531348c3f56e0e0

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: aggregation
sequences scored divided by scoring seconds, one run
Context-only references
evo2-cloud-operations reproduction run 30e7ae49: run receipt, Runpod L40S (P5, attempt-1)

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 60f60324a7cda6b66b370ea2569e71175f66a1baf64455d17b6a65813df02fd8

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: aggregation
sequences scored divided by scoring seconds, one run
Context-only references
evo2-cloud-operations recorded run b75c67aa: run receipt, Runpod L40S (P5, attempt-2)

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: d26432852833b76a63d4b91024cbe2c7a07a670dd5bbbcca2977f2139975a1eb

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: aggregation
sequences scored divided by scoring seconds, one run
Context-only references
evo2-cloud-operations: run log

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 9b42944eb2c1c7afeeb295f725bf1945ad8470f355b6a2e21531348c3f56e0e0

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: budget
one run per platform
Context-only references
evo2-cloud-operations reproduction run 30e7ae49: run receipt, Runpod L40S (P5, attempt-1)

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 60f60324a7cda6b66b370ea2569e71175f66a1baf64455d17b6a65813df02fd8

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: budget
one run per platform
Context-only references
evo2-cloud-operations recorded run b75c67aa: run receipt, Runpod L40S (P5, attempt-2)

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: d26432852833b76a63d4b91024cbe2c7a07a670dd5bbbcca2977f2139975a1eb

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: budget
one run per platform
Context-only references
evo2-cloud-operations: run log

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 9b42944eb2c1c7afeeb295f725bf1945ad8470f355b6a2e21531348c3f56e0e0

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

Comparison: dataset version
rewire-local-20261121-evo2ops-dataset-brca1-all
Context-only references
evo2-cloud-operations reproduction run 30e7ae49: run receipt, Runpod L40S (P5, attempt-1)

Original source ↗

evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: f8ae11c9a1c45505487c978b4cb7e064c4e59905
Retrieved: 2026-11-21T14:00:00Z

not individually reviewed

No individual claim review recorded

rewire run

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: 60f60324a7cda6b66b370ea2569e71175f66a1baf64455d17b6a65813df02fd8

Hash scope: complete bytes of the file at the pinned commit

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

3 source records and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: rewire-local-20261121-evo2ops-evaluation-evo2-7b-runpod-l40s-scoring-throughput

areas
dna-genomes
origin
rewire_run
execution scope
complete_selected_evaluation
protocol
Workload W1, batch size 1
version
f8ae11c9a1c45505487c978b4cb7e064c4e59905
eligible count
3893
scored count
3893
coverage
scored: 3893; eligible: 3893; unit: variants
timing seconds
w1 scoring seconds: 8532.602
peak memory
18021556224 bytes allocated (JSON pointer /results/w1/peak_memory_allocated_bytes)
inference hardware
NVIDIA L40S
comparison
protocol id: rewire-local-20261121-evo2ops-protocol-brca1-scoring-throughput; dataset version: rewire-local-20261121-evo2ops-dataset-brca1-all; split: none; every variant of the subset is scored; population: 3893/3893; inputs: variant and reference sequence, or the lookup score for the variant; adaptation: zero-shot inference; metric implementation: src/evo2ops/workloads.py; the recorded run used revision e93491a (evidence/runs/recorded-b75c67aa/provenance.json), an ancestor of the pinned commit; aggregation: sequences scored divided by scoring seconds, one run; budget: one run per platform
limitations
One run on one host. Throughput depends on the host as well as the GPU model.; The Runpod L40S value of the recorded run, 0.6117 sequences per second, was not repeated: the study's reproduction run 30e7ae49 measured 0.9081 on another L40S host for the same 5219 sequences, and the run log calls the recorded host a slower one.
source locator
evidence/runs/recorded-b75c67aa/platforms/P5/attempt-2/receipt-main.json, JSON pointer /results/w1
Related records

Suggest a correction