# Hierarchical Reasoning on ListOps Long Range Arena (test)

Source: [Hierarchical Reasoning on ListOps Long Range Arena (test)](<https://www.sota2.com/research/sota/hierarchical-reasoning-on-listops-long-range-arena-test>)

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

Data updated: 2026-02-26T05:32:17.691Z

Evaluation of model performance on the Hierarchical Reasoning task using the test split of the ListOps Long Range Arena 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 | Hierarchical Reasoning |
| Dataset (including any stated split) | ListOps Long Range Arena (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| 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/hierarchical-reasoning-on-listops-long-range-arena-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MS-SSM (S6) | 63.04 | Not recorded | 6955ff7f53fdd5c36173df50 |
| MS-SSM (S4) | 62.83 | Not recorded | 6955ff7f53fdd5c36173df50 |
| MULTIRESNET | 62.75 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Liquid-S4 | 62.75 | Not recorded | 6955ff7f53fdd5c36173df50 |
| S5 | 62.15 | Not recorded | 6955ff7f53fdd5c36173df50 |
| SGConv | 61.45 | Not recorded | 6955ff7f53fdd5c36173df50 |
| S4D | 60.52 | Not recorded | 6955ff7f53fdd5c36173df50 |
| S4 | 59.6 | Not recorded | 6955ff7f53fdd5c36173df50 |
| DSS | 57.6 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Mamba | 49.63 | Not recorded | 6955ff7f53fdd5c36173df50 |
| H-Transformer-1D | 49.53 | Not recorded | 6955ff7f53fdd5c36173df50 |
| CDIL | 44.05 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Mamba | 42.14 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Mamba | 38.02 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Reformer | 37.27 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Luna-256 | 37.25 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Transformer | 36.37 | Not recorded | 6955ff7f53fdd5c36173df50 |
| BigBird | 36.05 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Longformer | 35.63 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Sinkhorn Transformer | 33.67 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Griffin | 32.34 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Performer | 18.01 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Sparse Transformer | 17.07 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Linear Trans. | 16.13 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Linformer | 16.13 | Not recorded | 6955ff7f53fdd5c36173df50 |
| Local Attention | 15.82 | Not recorded | 6955ff7f53fdd5c36173df50 |

### MS-SSM (S6)

Accuracy: 63.04. Result ID: 699931d15698665ec49aa5df.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

Recorded evaluation configuration: {"Architecture type":"Convolutions + SSMs"}. This record does not assert independent reproduction.

### MS-SSM (S4)

Accuracy: 62.83. Result ID: 699931d15698665ec49aa5de.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

Recorded evaluation configuration: {"Architecture type":"Convolutions + SSMs"}. This record does not assert independent reproduction.

### MULTIRESNET

Accuracy: 62.75. Result ID: 699931d15698665ec49aa5d4.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1c8.md>)

[Implementation](<https://github.com/thjashin/multires-conv>)

Recorded evaluation configuration: {"Architecture type":"Convolutions"}. This record does not assert independent reproduction.

### Liquid-S4

Accuracy: 62.75. Result ID: 699931d15698665ec49aa5d9.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d801e209131cea3a185.md>)

[Implementation](<https://github.com/raminmh/liquid-s4>)

Recorded evaluation configuration: {"Architecture type":"SSMs"}. This record does not assert independent reproduction.

### S5

Accuracy: 62.15. Result ID: 699931d15698665ec49aa5d8.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eab1e209131cea4143a.md>)

[Implementation](<https://github.com/lindermanlab/S5>)

Recorded evaluation configuration: {"Architecture type":"SSMs"}. This record does not assert independent reproduction.

### SGConv

Accuracy: 61.45. Result ID: 699931d15698665ec49aa5d3.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dae1e209131cea3b798.md>)

Recorded evaluation configuration: {"Architecture type":"Convolutions"}. This record does not assert independent reproduction.

### S4D

Accuracy: 60.52. Result ID: 699931d15698665ec49aa5d7.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea3861c.md>)

Recorded evaluation configuration: {"Architecture type":"SSMs"}. This record does not assert independent reproduction.

### S4

Accuracy: 59.6. Result ID: 699931d15698665ec49aa5d5.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea38604.md>)

[Implementation](<https://github.com/HazyResearch/state-spaces>)

Recorded evaluation configuration: {"Architecture type":"SSMs"}. This record does not assert independent reproduction.

### DSS

Accuracy: 57.6. Result ID: 699931d15698665ec49aa5d6.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9d1e209131cea34f18.md>)

[Implementation](<https://github.com/ag1988/dss>)

Recorded evaluation configuration: {"Architecture type":"SSMs"}. This record does not assert independent reproduction.

### Mamba

Accuracy: 49.63. Result ID: 699931d15698665ec49aa5dc.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73611e209131cea5c0fe.md>)

Recorded evaluation configuration: {"Architecture type":"SSMs","Model size":"double model size (2x Param)"}. This record does not assert independent reproduction.

### H-Transformer-1D

Accuracy: 49.53. Result ID: 699931d15698665ec49aa5d1.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a761e209131cea284dd.md>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### CDIL

Accuracy: 44.05. Result ID: 699931d15698665ec49aa5d2.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca51e209131cea3532d.md>)

[Implementation](<https://github.com/LeiCheng-no/CDIL-CNN>)

Recorded evaluation configuration: {"Architecture type":"Convolutions"}. This record does not assert independent reproduction.

### Mamba

Accuracy: 42.14. Result ID: 699931d15698665ec49aa5dd.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73611e209131cea5c0fe.md>)

Recorded evaluation configuration: {"Architecture type":"SSMs","State size":"double state size (2x State)"}. This record does not assert independent reproduction.

### Mamba

Accuracy: 38.02. Result ID: 699931d15698665ec49aa5db.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73611e209131cea5c0fe.md>)

Recorded evaluation configuration: {"Architecture type":"SSMs"}. This record does not assert independent reproduction.

### Reformer

Accuracy: 37.27. Result ID: 699931d15698665ec49aa5d0.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671b1e209131cea143ed.md>)

[Implementation](<https://github.com/google/trax/tree/master/trax/models/reformer>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Luna-256

Accuracy: 37.25. Result ID: 699931d15698665ec49aa5cf.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b291e209131cea2c661.md>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Transformer

Accuracy: 36.37. Result ID: 699931d15698665ec49aa5c6.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

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

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

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### BigBird

Accuracy: 36.05. Result ID: 699931d15698665ec49aa5ce.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690b1e209131cea1faf6.md>)

[Implementation](<http://goo.gle/bigbird-transformer>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Longformer

Accuracy: 35.63. Result ID: 699931d15698665ec49aa5cd.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d41e209131cea1e701.md>)

[Implementation](<https://github.com/allenai/longformer>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Sinkhorn Transformer

Accuracy: 33.67. Result ID: 699931d15698665ec49aa5cc.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67191e209131cea142f7.md>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Griffin

Accuracy: 32.34. Result ID: 699931d15698665ec49aa5da.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72571e209131cea55cb4.md>)

Recorded evaluation configuration: {"Architecture type":"SSMs"}. This record does not assert independent reproduction.

### Performer

Accuracy: 18.01. Result ID: 699931d15698665ec49aa5cb.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d699.md>)

[Implementation](<https://github.com/google-research/google-research/tree/master/performer>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Sparse Transformer

Accuracy: 17.07. Result ID: 699931d15698665ec49aa5ca.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65aa1e209131cea0bc26.md>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Linear Trans.

Accuracy: 16.13. Result ID: 699931d15698665ec49aa5c8.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68471e209131cea1b069.md>)

[Implementation](<https://linear-transformers.com/>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Linformer

Accuracy: 16.13. Result ID: 699931d15698665ec49aa5c9.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

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

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

### Local Attention

Accuracy: 15.82. Result ID: 699931d15698665ec49aa5c7.

[Reporting paper](<https://www.sota2.com/research/paper/6955ff7f53fdd5c36173df50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68bd1e209131cea1dee1.md>)

[Implementation](<https://github.com/google-research/long-range-arena>)

Recorded evaluation configuration: {"Architecture type":"Transformers"}. This record does not assert independent reproduction.

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