# Natural Language to FHIRPath query generation on FHIRPath-QA Clinical perspective

Source: [Natural Language to FHIRPath query generation on FHIRPath-QA Clinical perspective](<https://www.sota2.com/research/sota/natural-language-to-fhirpath-query-generation-on-fhirpath-qa-clinical-perspective>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-26T13:27:19.775Z

Evaluation of models generating executable FHIRPath queries from natural language instructions using the FHIRPath-QA Clinical perspective dataset.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Natural Language to FHIRPath query generation |
| Dataset (including any stated split) | FHIRPath-QA Clinical perspective |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/natural-language-to-fhirpath-query-generation-on-fhirpath-qa-clinical-perspective.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Failure Rate](<https://www.sota2.com/research/sota/natural-language-to-fhirpath-query-generation-on-fhirpath-qa-clinical-perspective.md?metric=Failure%20Rate>): Lower is better; unit: PERCENT.

- [Accuracy (Excl. Failures)](<https://www.sota2.com/research/sota/natural-language-to-fhirpath-query-generation-on-fhirpath-qa-clinical-perspective.md?metric=Accuracy%20(Excl.%20Failures)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| o1-preview | 42 | Not recorded | 69a5197d2d603e6de3e3c913 |
| o1-mini | 35 | Not recorded | 69a5197d2d603e6de3e3c913 |
| o1-mini | 33 | Not recorded | 69a5197d2d603e6de3e3c913 |
| o1-preview | 25 | Not recorded | 69a5197d2d603e6de3e3c913 |
| 4o-mini | 25 | Not recorded | 69a5197d2d603e6de3e3c913 |
| 4o-mini | 24 | Not recorded | 69a5197d2d603e6de3e3c913 |

### o1-preview

Accuracy: 42. Result ID: 69c5332e47f34ce924aeba14.

[Reporting paper](<https://www.sota2.com/research/paper/69a5197d2d603e6de3e3c913.md>)

Recorded evaluation configuration: {"Architecture Strategy":"Retrieval"}. This record does not assert independent reproduction.

### o1-mini

Accuracy: 35. Result ID: 69c5332e47f34ce924aeba16.

[Reporting paper](<https://www.sota2.com/research/paper/69a5197d2d603e6de3e3c913.md>)

Recorded evaluation configuration: {"Architecture Strategy":"Query-first"}. This record does not assert independent reproduction.

### o1-mini

Accuracy: 33. Result ID: 69c5332e47f34ce924aeba13.

[Reporting paper](<https://www.sota2.com/research/paper/69a5197d2d603e6de3e3c913.md>)

Recorded evaluation configuration: {"Architecture Strategy":"Retrieval"}. This record does not assert independent reproduction.

### o1-preview

Accuracy: 25. Result ID: 69c5332e47f34ce924aeba17.

[Reporting paper](<https://www.sota2.com/research/paper/69a5197d2d603e6de3e3c913.md>)

Recorded evaluation configuration: {"Architecture Strategy":"Query-first"}. This record does not assert independent reproduction.

### 4o-mini

Accuracy: 25. Result ID: 69c5332e47f34ce924aeba18.

[Reporting paper](<https://www.sota2.com/research/paper/69a5197d2d603e6de3e3c913.md>)

Recorded evaluation configuration: {"Architecture Strategy":"Query-first"}. This record does not assert independent reproduction.

### 4o-mini

Accuracy: 24. Result ID: 69c5332e47f34ce924aeba15.

[Reporting paper](<https://www.sota2.com/research/paper/69a5197d2d603e6de3e3c913.md>)

Recorded evaluation configuration: {"Architecture Strategy":"Retrieval"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.