# Long-range sequence modeling on ListOps Long Range Arena (LRA) 2K (test)

Source: [Long-range sequence modeling on ListOps Long Range Arena (LRA) 2K (test)](<https://www.sota2.com/research/sota/long-range-sequence-modeling-on-listops-long-range-arena-lra-2k-test>)

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

Data updated: 2026-02-26T05:30:06.640Z

Evaluation of long-range sequence modeling performance specifically on the ListOps 2K subset of the Long Range Arena (LRA) benchmark, using the test split.

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 | Long-range sequence modeling |
| Dataset (including any stated split) | ListOps Long Range Arena (LRA) 2K (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/long-range-sequence-modeling-on-listops-long-range-arena-lra-2k-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Efficient Attention + GFSA | 37.9 | Not recorded | 68fa758e1e209131cea68985 |
| Transformer+GFSA | 37.6 | Not recorded | 68fa758e1e209131cea68985 |
| Linformer | 37.3 | Not recorded | 68fa758e1e209131cea68985 |
| YOSO-E | 37.3 | Not recorded | 68fa758e1e209131cea68985 |
| Transformer | 37.1 | Not recorded | 68fa758e1e209131cea68985 |
| Efficient Attention | 36.9 | Not recorded | 68fa758e1e209131cea68985 |

### Efficient Attention + GFSA

Accuracy: 37.9. Result ID: 6993c6c63a6c3148491871a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

Recorded evaluation configuration: {"Runtime (s per 1,000 steps)":53.8,"GPU usage (GB)":0.67}. This record does not assert independent reproduction.

### Transformer+GFSA

Accuracy: 37.6. Result ID: 6993c6c63a6c31484918719c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

Recorded evaluation configuration: {"Runtime (s per 1,000 steps)":635.8,"GPU usage (GB)":10.87}. This record does not assert independent reproduction.

### Linformer

Accuracy: 37.3. Result ID: 6993c6c63a6c31484918719d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67bb1e209131cea182c9.md>)

Recorded evaluation configuration: {"Runtime (s per 1,000 steps)":63.4,"GPU usage (GB)":1.73}. This record does not assert independent reproduction.

### YOSO-E

Accuracy: 37.3. Result ID: 6993c6c63a6c31484918719e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b421e209131cea2d02f.md>)

Recorded evaluation configuration: {"Runtime (s per 1,000 steps)":85.7,"GPU usage (GB)":0.37}. This record does not assert independent reproduction.

### Transformer

Accuracy: 37.1. Result ID: 6993c6c63a6c31484918719b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Runtime (s per 1,000 steps)":198.3,"GPU usage (GB)":5.5}. This record does not assert independent reproduction.

### Efficient Attention

Accuracy: 36.9. Result ID: 6993c6c63a6c31484918719f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa758e1e209131cea68985.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea5346b.md>)

[Implementation](<https://github.com/cmsflash/efficient-attention>)

Recorded evaluation configuration: {"Runtime (s per 1,000 steps)":49.2,"GPU usage (GB)":0.57}. This record does not assert independent reproduction.

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