# Zero-shot Evaluation Suite (WikiText2, PTB, BoolQ, PIQA, HellaSwag, WinoGrande, ARC, OBQA)

Source: [Zero-shot Evaluation Suite (WikiText2, PTB, BoolQ, PIQA, HellaSwag, WinoGrande, ARC, OBQA)](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa>)

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

Data updated: 2026-03-12T08:03:46.361Z

A zero-shot evaluation suite combining performance metrics across language modeling (WikiText2, PTB) and various reasoning/QA tasks (BoolQ, PIQA, HellaSwag, WinoGrande, ARC, OBQA).

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 Evaluation |
| Dataset (including any stated split) | WikiText2, PTB, BoolQ, PIQA, HellaSwag, WinoGrande, ARC, OBQA |
| Metric | PTB Perplexity |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [PTB Perplexity](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=PTB%20Perplexity>): Lower is better; unit: SCALAR.

- [WikiText2 Score](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=WikiText2%20Score>): Higher is better; unit: PERCENT.

- [BoolQ Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=BoolQ%20Accuracy>): Higher is better; unit: PERCENT.

- [PIQA Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=PIQA%20Accuracy>): Higher is better; unit: PERCENT.

- [HellaSwag Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=HellaSwag%20Accuracy>): Higher is better; unit: PERCENT.

- [WinoGrande Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=WinoGrande%20Accuracy>): Higher is better; unit: PERCENT.

- [ARC-e Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=ARC-e%20Accuracy>): Higher is better; unit: PERCENT.

- [ARC-c Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=ARC-c%20Accuracy>): Higher is better; unit: PERCENT.

- [OBQA Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=OBQA%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

- [WikiText2 Perplexity](<https://www.sota2.com/research/sota/zero-shot-evaluation-suite-wikitext2-ptb-boolq-piqa-hellaswag-winogrande-arc-obqa.md?metric=WikiText2%20Perplexity>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PTB Perplexity | Result date | Report paper |
| --- | --- | --- | --- |
| LLaMA-2-7B | 28.99 | Not recorded | 68fa76891e209131cea6d801 |
| HyWIA | 29.61 | Not recorded | 68fa76891e209131cea6d801 |
| Vicuna-7B | 58.19 | Not recorded | 68fa76891e209131cea6d801 |
| LLM-Pruner Vector | 74.66 | Not recorded | 68fa76891e209131cea6d801 |
| LLM-Pruner Element² | 76.78 | Not recorded | 68fa76891e209131cea6d801 |
| HyWIA | 174.19 | Not recorded | 68fa76891e209131cea6d801 |
| LLM-Pruner Vector | 214.25 | Not recorded | 68fa76891e209131cea6d801 |
| LLM-Pruner Element² | 258.44 | Not recorded | 68fa76891e209131cea6d801 |

### LLaMA-2-7B

PTB Perplexity: 28.99. Result ID: 69b272446dbb7075b95cd8da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

Recorded evaluation configuration: {"Ratio":"0%"}. This record does not assert independent reproduction.

### HyWIA

PTB Perplexity: 29.61. Result ID: 69b272446dbb7075b95cd903.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

Recorded evaluation configuration: {"Pruning Ratio":"20%","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Vicuna-7B

PTB Perplexity: 58.19. Result ID: 69b272446dbb7075b95cd900.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

Recorded evaluation configuration: {"Pruning Ratio":"0%","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### LLM-Pruner Vector

PTB Perplexity: 74.66. Result ID: 69b272446dbb7075b95cd901.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70af1e209131cea4c8b2.md>)

[Implementation](<https://github.com/horseee/LLM-Pruner>)

Recorded evaluation configuration: {"Pruning Ratio":"20%","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### LLM-Pruner Element²

PTB Perplexity: 76.78. Result ID: 69b272446dbb7075b95cd902.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70af1e209131cea4c8b2.md>)

[Implementation](<https://github.com/horseee/LLM-Pruner>)

Recorded evaluation configuration: {"Pruning Ratio":"20%","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### HyWIA

PTB Perplexity: 174.19. Result ID: 69b272446dbb7075b95cd8dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

Recorded evaluation configuration: {"Ratio":"50%"}. This record does not assert independent reproduction.

### LLM-Pruner Vector

PTB Perplexity: 214.25. Result ID: 69b272446dbb7075b95cd8db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70af1e209131cea4c8b2.md>)

[Implementation](<https://github.com/horseee/LLM-Pruner>)

Recorded evaluation configuration: {"Ratio":"50%"}. This record does not assert independent reproduction.

### LLM-Pruner Element²

PTB Perplexity: 258.44. Result ID: 69b272446dbb7075b95cd8dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70af1e209131cea4c8b2.md>)

[Implementation](<https://github.com/horseee/LLM-Pruner>)

Recorded evaluation configuration: {"Ratio":"50%"}. This record does not assert independent reproduction.

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