# Zero-shot Prediction on RTE

Source: [Zero-shot Prediction on RTE](<https://www.sota2.com/research/sota/zero-shot-prediction-on-rte>)

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

Data updated: 2026-02-27T14:22:04.771Z

Evaluation of zero-shot prediction performance on the RTE dataset, typically measured by accuracy.

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 | Zero-shot Prediction |
| Dataset (including any stated split) | RTE |
| Metric | Zero-shot Accuracy (RTE) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Zero-shot Accuracy (RTE)](<https://www.sota2.com/research/sota/zero-shot-prediction-on-rte.md?metric=Zero-shot%20Accuracy%20(RTE)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Zero-shot Accuracy (RTE) | Result date | Report paper |
| --- | --- | --- | --- |
| Dense | 62.82 | Not recorded | 68fa7bd41e209131cea8ac27 |
| L-ADMM | 58.12 | Not recorded | 68fa7bd41e209131cea8ac27 |
| SparseLLM | 57.4 | Not recorded | 68fa7bd41e209131cea8ac27 |
| SparseGPT | 56.68 | Not recorded | 68fa7bd41e209131cea8ac27 |
| SparseLLM | 56.68 | Not recorded | 68fa7bd41e209131cea8ac27 |
| SparseGPT | 56.32 | Not recorded | 68fa7bd41e209131cea8ac27 |
| L-ADMM | 56.32 | Not recorded | 68fa7bd41e209131cea8ac27 |
| ALPS | 55.96 | Not recorded | 68fa7bd41e209131cea8ac27 |
| ALPS | 55.6 | Not recorded | 68fa7bd41e209131cea8ac27 |
| Wanda | 54.15 | Not recorded | 68fa7bd41e209131cea8ac27 |
| Wanda | 53.07 | Not recorded | 68fa7bd41e209131cea8ac27 |
| SAFE | 53.07 | Not recorded | 68fa7bd41e209131cea8ac27 |
| SAFE | 53.07 | Not recorded | 68fa7bd41e209131cea8ac27 |
| ELSA | 53.07 | Not recorded | 68fa7bd41e209131cea8ac27 |
| ELSA | 52.71 | Not recorded | 68fa7bd41e209131cea8ac27 |
| Magnitude | 52.35 | Not recorded | 68fa7bd41e209131cea8ac27 |
| Magnitude | 52.35 | Not recorded | 68fa7bd41e209131cea8ac27 |

### Dense

Zero-shot Accuracy (RTE): 62.82. Result ID: 69a1a88b35dfcabb00e80799.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

Recorded evaluation configuration: {"Sparsity":"0%","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### L-ADMM

Zero-shot Accuracy (RTE): 58.12. Result ID: 69a1a88b35dfcabb00e807a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60734.md>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### SparseLLM

Zero-shot Accuracy (RTE): 57.4. Result ID: 69a1a88b35dfcabb00e807a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### SparseGPT

Zero-shot Accuracy (RTE): 56.68. Result ID: 69a1a88b35dfcabb00e807a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecc1e209131cea42371.md>)

[Implementation](<https://github.com/IST-DASLab/sparsegpt>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### SparseLLM

Zero-shot Accuracy (RTE): 56.68. Result ID: 69a1a88b35dfcabb00e807a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### SparseGPT

Zero-shot Accuracy (RTE): 56.32. Result ID: 69a1a88b35dfcabb00e8079c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecc1e209131cea42371.md>)

[Implementation](<https://github.com/IST-DASLab/sparsegpt>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### L-ADMM

Zero-shot Accuracy (RTE): 56.32. Result ID: 69a1a88b35dfcabb00e8079d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60734.md>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### ALPS

Zero-shot Accuracy (RTE): 55.96. Result ID: 69a1a88b35dfcabb00e807a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b1f1e209131cea86ad5.md>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### ALPS

Zero-shot Accuracy (RTE): 55.6. Result ID: 69a1a88b35dfcabb00e8079e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b1f1e209131cea86ad5.md>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### Wanda

Zero-shot Accuracy (RTE): 54.15. Result ID: 69a1a88b35dfcabb00e807a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73281e209131cea5ac45.md>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### Wanda

Zero-shot Accuracy (RTE): 53.07. Result ID: 69a1a88b35dfcabb00e8079b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73281e209131cea5ac45.md>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### SAFE

Zero-shot Accuracy (RTE): 53.07. Result ID: 69a1a88b35dfcabb00e8079f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79731e209131cea7db09.md>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### SAFE

Zero-shot Accuracy (RTE): 53.07. Result ID: 69a1a88b35dfcabb00e807a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79731e209131cea7db09.md>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### ELSA

Zero-shot Accuracy (RTE): 53.07. Result ID: 69a1a88b35dfcabb00e807a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### ELSA

Zero-shot Accuracy (RTE): 52.71. Result ID: 69a1a88b35dfcabb00e807a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### Magnitude

Zero-shot Accuracy (RTE): 52.35. Result ID: 69a1a88b35dfcabb00e8079a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622d1e209131ce9f7f15.md>)

Recorded evaluation configuration: {"Sparsity":"2:4","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

### Magnitude

Zero-shot Accuracy (RTE): 52.35. Result ID: 69a1a88b35dfcabb00e807a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd41e209131cea8ac27.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa622d1e209131ce9f7f15.md>)

Recorded evaluation configuration: {"Sparsity":"4:8","Backbone":"LLaMA-2-7B","Zero-shot":"true"}. This record does not assert independent reproduction.

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