# Expert Preference Pairwise on LMArena Expert Med

Source: [Expert Preference Pairwise on LMArena Expert Med](<https://www.sota2.com/research/sota/expert-preference-pairwise-on-lmarena-expert-med>)

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

Data updated: 2026-04-07T09:31:07.669Z

Evaluation of model performance using Expert Preference Pairwise comparison methodology on the LMArena Expert Med dataset, measured by 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 | Expert Preference Pairwise |
| Dataset (including any stated split) | LMArena Expert Med |
| 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/expert-preference-pairwise-on-lmarena-expert-med.md?metric=Kendall%27s%20tau_b>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Kendall's tau\_b | Result date | Report paper |
| --- | --- | --- | --- |
| IRT(All) Ranking | 0.476 | Not recorded | 68fa7bb61e209131cea8a13e |
| IRT (pr.) Ranking | 0.476 | Not recorded | 68fa7bb61e209131cea8a13e |
| Accuracy Ranking | 0.438 | Not recorded | 68fa7bb61e209131cea8a13e |

### IRT(All) Ranking

Kendall's tau\_b: 0.476. Result ID: 69d4ceda47f34ce924bcec59.

[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":"21","Domain (Format)":"Exp Prefer (Pairwise)"}. This record does not assert independent reproduction.

### IRT (pr.) Ranking

Kendall's tau\_b: 0.476. Result ID: 69d4ceda47f34ce924bcec5a.

[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":"21","Domain (Format)":"Exp Prefer (Pairwise)"}. This record does not assert independent reproduction.

### Accuracy Ranking

Kendall's tau\_b: 0.438. Result ID: 69d4ceda47f34ce924bcec58.

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

Recorded evaluation configuration: {"n":"21","Domain (Format)":"Exp Prefer (Pairwise)"}. This record does not assert independent reproduction.

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