# Medical Chat Evaluation on MEDIC HealthBench

Source: [Medical Chat Evaluation on MEDIC HealthBench](<https://www.sota2.com/research/sota/medical-chat-evaluation-on-medic-healthbench>)

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

Data updated: 2026-04-07T09:31:07.709Z

Evaluation of model performance on medical chat scenarios using the MEDIC HealthBench dataset, typically assessed using correlation metrics such as Kendall's tau\_b.

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 | Medical Chat Evaluation |
| Dataset (including any stated split) | MEDIC HealthBench |
| Metric | Kendall's Tau-b |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Kendall's Tau-b](<https://www.sota2.com/research/sota/medical-chat-evaluation-on-medic-healthbench.md?metric=Kendall%27s%20Tau-b>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Kendall's Tau-b | Result date | Report paper |
| --- | --- | --- | --- |
| Accuracy Ranking | 0.546 | Not recorded | 68fa7bb61e209131cea8a13e |
| IRT(All) Ranking | 0.546 | Not recorded | 68fa7bb61e209131cea8a13e |
| IRT (pr.) Ranking | 0.546 | Not recorded | 68fa7bb61e209131cea8a13e |

### Accuracy Ranking

Kendall's Tau-b: 0.546. Result ID: 69d4ceda47f34ce924bcec5e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

Recorded evaluation configuration: {"n":"8","Domain (Format)":"Chat (LLM-Rubric)"}. This record does not assert independent reproduction.

### IRT(All) Ranking

Kendall's Tau-b: 0.546. Result ID: 69d4ceda47f34ce924bcec5f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

Recorded evaluation configuration: {"n":"8","Domain (Format)":"Chat (LLM-Rubric)"}. This record does not assert independent reproduction.

### IRT (pr.) Ranking

Kendall's Tau-b: 0.546. Result ID: 69d4ceda47f34ce924bcec60.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb61e209131cea8a13e.md>)

Recorded evaluation configuration: {"n":"8","Domain (Format)":"Chat (LLM-Rubric)"}. This record does not assert independent reproduction.

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