# Labeling Task Performance on 80-session Set (4-fold CV)

Source: [Labeling Task Performance on 80-session Set (4-fold CV)](<https://www.sota2.com/research/sota/labeling-task-performance-on-80-session-set-4-fold-cv>)

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

Data updated: 2026-03-31T08:50:35.736Z

Evaluation of general labeling task performance across four cross-validation folds on the 80-session dataset, reporting mean and standard deviation across folds.

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 | Labeling task performance |
| Dataset (including any stated split) | 80-session set 4-fold cross-validation (test) |
| Metric | Fold 0 Performance |
| Unit | PERCENT |
| 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

- [Fold 0 Performance](<https://www.sota2.com/research/sota/labeling-task-performance-on-80-session-set-4-fold-cv.md?metric=Fold%200%20Performance>): Higher is better; unit: PERCENT.

- [Fold 1 Performance](<https://www.sota2.com/research/sota/labeling-task-performance-on-80-session-set-4-fold-cv.md?metric=Fold%201%20Performance>): Higher is better; unit: PERCENT.

- [Fold 2 Performance](<https://www.sota2.com/research/sota/labeling-task-performance-on-80-session-set-4-fold-cv.md?metric=Fold%202%20Performance>): Higher is better; unit: PERCENT.

- [Fold 3 Performance](<https://www.sota2.com/research/sota/labeling-task-performance-on-80-session-set-4-fold-cv.md?metric=Fold%203%20Performance>): Higher is better; unit: PERCENT.

- [Mean Performance](<https://www.sota2.com/research/sota/labeling-task-performance-on-80-session-set-4-fold-cv.md?metric=Mean%20Performance>): Higher is better; unit: PERCENT.

- [Performance Standard Deviation](<https://www.sota2.com/research/sota/labeling-task-performance-on-80-session-set-4-fold-cv.md?metric=Performance%20Standard%20Deviation>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Fold 0 Performance | Result date | Report paper |
| --- | --- | --- | --- |
| Codex | 85 | Not recorded | 69cb55020636e5bf4afc9ec7 |
| Claude | 71 | Not recorded | 69cb55020636e5bf4afc9ec7 |
| Gemini | 71 | Not recorded | 69cb55020636e5bf4afc9ec7 |

### Codex

Fold 0 Performance: 85. Result ID: 69cb8ac747f34ce924b3f09c.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55020636e5bf4afc9ec7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb55020636e5bf4afc9ec7.md>)

Recorded evaluation configuration: {"Iteration strategy":"Agent-driven iteration"}. This record does not assert independent reproduction.

### Claude

Fold 0 Performance: 71. Result ID: 69cb8ac747f34ce924b3f09d.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55020636e5bf4afc9ec7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb55020636e5bf4afc9ec7.md>)

Recorded evaluation configuration: {"Iteration strategy":"Agent-driven iteration"}. This record does not assert independent reproduction.

### Gemini

Fold 0 Performance: 71. Result ID: 69cb8ac747f34ce924b3f09e.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55020636e5bf4afc9ec7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb55020636e5bf4afc9ec7.md>)

Recorded evaluation configuration: {"Iteration strategy":"Agent-driven iteration"}. This record does not assert independent reproduction.

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