Configuration

GPT-5 2025-08-07 with CIViC MCP, March 2026

OpenAI Agents SDK + FastMCP; new subprocess/query, auto tool selection, default 10 model/tool cycles.

Overview

OpenAI Agents SDK + FastMCP; new subprocess/query, auto tool selection, default 10 model/tool cycles.

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

Evaluations and results

1 evaluation · 54 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	0.95 overall_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Fig1c Overall Accuracy; Section 3
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	0.95 diagnostic_micro_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Figure 1c, diagnostic row, mcp column
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	0.66 diagnostic_negative_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Diagnostic / Negative, f1
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 diagnostic_negative_precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Diagnostic / Negative, precision
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	0.5 diagnostic_negative_recall fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Diagnostic / Negative, recall
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 diagnostic_positive_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Diagnostic / Positive, f1
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 diagnostic_positive_precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Diagnostic / Positive, precision
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 diagnostic_positive_recall fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Diagnostic / Positive, recall
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_dominant_negative_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Dominant Negative, f1
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_dominant_negative_precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Dominant Negative, precision
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_dominant_negative_recall fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Dominant Negative, recall
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_micro_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Figure 1c, functional row, mcp column
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_gain_of_function_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Gain of Function, f1
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_gain_of_function_precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Gain of Function, precision
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_gain_of_function_recall fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Gain of Function, recall
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_loss_of_function_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Loss of Function, f1
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_loss_of_function_precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Loss of Function, precision
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_loss_of_function_recall fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Loss of Function, recall
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_unaltered_function_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Unaltered Function, f1
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_unaltered_function_precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Unaltered Function, precision
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 functional_unaltered_function_recall fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Functional / Unaltered Function, recall
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	0.98 micro_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Fig1c Micro F1; Section 3
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 oncogenic_micro_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP: integrating large language models with the Clinical Interpretations of Variants in Cancer · Figure 1c, oncogenic row, mcp column
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	0.96 oncogenic_oncogenicity_f1 F1 score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Oncogenic / Oncogenicity, f1
Configuration: GPT-5 2025-08-07 with CIViC MCP, March 2026	Protocol: CIViC evidence-direction retrieval, March 2026 Dataset: CIViC 100 molecular-profile/disease/therapy triplets, March 2026	1 oncogenic_oncogenicity_precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CIViC mcp retrieval Not reported Aggregation: Not reported CIViC MCP supplementary methods and complete Tables 1–3 · Supplementary Table 1, Oncogenic / Oncogenicity, precision

Source checking is not independent reproduction. Release 2026-09-30-e37e3ab1284d.

Use this model

How it works, versions and access

Related profile: CIViC fixed-schema evidence retrieval evaluation workflow. This page retains the exact record and its evaluation context.

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-30-e37e3ab1284d
Property and statement	Original source and location	Review and provenance
Relationship: variant of uc-clinical-20260930-pipeline-civic-retrieval Individual claims	CIViC MCP supplementary methods and complete Tables 1–3 Original source ↗ Supplementary implementation and Agent Mode evaluation methods Version: vbag209_supplementary_data.docx, final article supplement Retrieved: 2026-09-30T21:25:48Z	source checked automated source review · 2026-09-30 Audit details Transcription from inspected primary source. No execution, independent replication or human scientific review. Field: `links:variant_of:uc-clinical-20260930-pipeline-civic-retrieval` Claim: uc-clinical-20260930-association-civic-gpt5-mcp Source artifact SHA-256: `857b272f9f29b9cb35d4fba7f424ef31d664d8acf8a23475c7c626a452b2e9e6` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

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

Sources and history

View linked audit checks and correction history

Release 2026-09-30-e37e3ab1284d · Record review: source checked

1 source records and release history

CIViC MCP supplementary methods and complete Tables 1–3 · Original source · vbag209_supplementary_data.docx, final article supplement

Download this release

Technical metadata and extraction receipts

Stable ID: uc-clinical-20260930-civic-gpt5-mcp

areas: dna-genomes
contexts: clinical_research
review: method: automated_source_review; reviewer: Codex clinical coverage worker; 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-supp
model version: gpt-5-2025-08-07
runtime: Python 3.11.7
temperature note: Main text says temperature=1; supplement says API default and temperature not exposed. Preserve discrepancy; use supplementary configuration.
parent identity review: source id: uc-clinical-20260930-source-civic-supp; source locator: Supplementary implementation and Agent Mode evaluation methods; method: automated_source_review

Related records

variant of: CIViC fixed-schema evidence retrieval evaluation workflow
subject: Configuration identity: GPT-5 2025-08-07 with CIViC MCP, March 2026
configuration: CIViC mcp retrieval

Suggest a correction