rewirebio.iobenchmarks
Result

Runtime (mean per query) of GPT-5 2025-08-07 alone, CIViC March 2026 on CIViC 100 molecular-profile/disease/therapy triplets, March 2026

42.9 Runtime (mean per query)

Methods

Tested configuration
GPT-5 2025-08-07 alone, CIViC March 2026
Protocol
CIViC evidence-direction retrieval, March 2026
Dataset
CIViC 100 molecular-profile/disease/therapy triplets, March 2026
Related family profiles
CIViC fixed-schema evidence retrieval evaluation workflow
Evaluation
CIViC alone retrieval
Coverage
Not reported scored / Not reported eligible
Uncertainty
95% CI 40.0 to 45.8
Evidence
Author-reported evaluation · source checkedCIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Fig1c Mean Time Seconds; Section 3

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split
Not reported
Adaptation
Not reported
Scoring implementation
Source-defined endpoint; see result source_locator

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Reported result
42.9
Individual claims
CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer

Original source ↗

Fig1c Mean Time Seconds; Section 3

Version: Final article corrected and typeset 12 August 2026
Retrieved: 2026-09-30T21:24:15Z

source checked

["automated-source-review"] · 2026-09-30

author reported

Audit details

Transcription from inspected primary source. No execution, independent replication or human scientific review.

Field: attributes.printed_value

Source artifact SHA-256: 1bebf491323f252d27539a73da04fab4dacf7e3f83b531ee9262645f79e40bad

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Sources and history

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

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

Stable ID: uc-clinical-20260930-civic-alone-time

areas
dna-genomes
contexts
clinical_research
metric
runtime
unit
second
printed value
42.9
numeric value
42.9
metric direction
lower
uncertainty
type: confidence_interval; level: 0.95; lower: 40.0; upper: 45.8; printed: 40.0–45.8
source locator
Fig1c Mean Time Seconds; Section 3
review
method: automated-source-review; reviewer: codex; date: 2026-09-30; note: Transcription from inspected primary source. No execution, independent replication or human scientific review.; source id: uc-clinical-20260930-source-civic; reviewer note: role: clinical coverage worker
denominator
100
metric qualifier
mean per query
Related records

Suggest a correction