# Temporal Relation Classification on TimeBankNT (test)

Source: [Temporal Relation Classification on TimeBankNT (test)](<https://www.sota2.com/research/sota/temporal-relation-classification-on-timebanknt-test>)

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

Data updated: 2026-04-15T07:12:08.144Z

Evaluation of Temporal Relation Classification performance on the test split of the TimeBankNT 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 | Temporal Relation Classification |
| Dataset (including any stated split) | TimeBankNT (test) |
| 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/temporal-relation-classification-on-timebanknt-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/temporal-relation-classification-on-timebanknt-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/temporal-relation-classification-on-timebanknt-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/temporal-relation-classification-on-timebanknt-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Human performance | 73 | Not recorded | 68fa6e3d1e209131cea3e913 |
| LongT5 XL | 47 | Not recorded | 68fa6e3d1e209131cea3e913 |
| LongT5 Large | 45 | Not recorded | 68fa6e3d1e209131cea3e913 |
| LongT5 Base | 44 | Not recorded | 68fa6e3d1e209131cea3e913 |
| Most frequent class | 30 | Not recorded | 68fa6e3d1e209131cea3e913 |
| “Later is after” heuristic | 30 | Not recorded | 68fa6e3d1e209131cea3e913 |

### Human performance

Accuracy: 73. Result ID: 69df387747f34ce924c78344.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LongT5 XL

Accuracy: 47. Result ID: 69df387747f34ce924c78343.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

Recorded evaluation configuration: {"Number of Parameters":"1253M","Architecture":"Transformer-based"}. This record does not assert independent reproduction.

### LongT5 Large

Accuracy: 45. Result ID: 69df387747f34ce924c78342.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

Recorded evaluation configuration: {"Number of Parameters":"349M","Architecture":"Transformer-based"}. This record does not assert independent reproduction.

### LongT5 Base

Accuracy: 44. Result ID: 69df387747f34ce924c78341.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

Recorded evaluation configuration: {"Number of Parameters":"114M","Architecture":"Transformer-based"}. This record does not assert independent reproduction.

### Most frequent class

Accuracy: 30. Result ID: 69df387747f34ce924c7833f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### “Later is after” heuristic

Accuracy: 30. Result ID: 69df387747f34ce924c78340.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e3d1e209131cea3e913.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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