# Zero-shot Evaluation on ARC-E, BoolQ, HSwag, LAMBADA, OBQA, PIQA, SocIQA, and WinoGr (test)

Source: [Zero-shot Evaluation on ARC-E, BoolQ, HSwag, LAMBADA, OBQA, PIQA, SocIQA, and WinoGr (test)](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test>)

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

Data updated: 2026-03-11T07:08:24.377Z

Zero-shot performance evaluation across a specific suite of eight reasoning and knowledge benchmarks: ARC-E, BoolQ, HSwag, LAMBADA, OpenBookQA (OBQA), PIQA, SocialIQA (SocIQA), and WinoGrande (WinoGr test set).

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) | ARC-E, BoolQ, HSwag, LAMBADA, OBQA, PIQA, SocIQA, WinoGr (test) |
| Metric | ARC-E 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

- [ARC-E Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=ARC-E%20Accuracy>): Higher is better; unit: PERCENT.

- [BoolQ Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=BoolQ%20Accuracy>): Higher is better; unit: PERCENT.

- [HSwag Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=HSwag%20Accuracy>): Higher is better; unit: PERCENT.

- [LAMBADA Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=LAMBADA%20Accuracy>): Higher is better; unit: PERCENT.

- [OBQA Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=OBQA%20Accuracy>): Higher is better; unit: PERCENT.

- [PIQA Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=PIQA%20Accuracy>): Higher is better; unit: PERCENT.

- [SocIQA Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=SocIQA%20Accuracy>): Higher is better; unit: PERCENT.

- [WinoGr Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=WinoGr%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Improvement](<https://www.sota2.com/research/sota/zero-shot-evaluation-on-arc-e-boolq-hswag-lambada-obqa-piqa-sociqa-and-winogr-test.md?metric=Average%20Improvement>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ARC-E Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| XSA | 60.65 | Not recorded | 69b0f6f82d603e6de3e45c92 |
| XSA | 58.84 | Not recorded | 69b0f6f82d603e6de3e45c92 |
| Transformer Baseline | 58.59 | Not recorded | 69b0f6f82d603e6de3e45c92 |
| Transformer Baseline | 56.19 | Not recorded | 69b0f6f82d603e6de3e45c92 |
| XSA | 52.69 | Not recorded | 69b0f6f82d603e6de3e45c92 |
| Transformer Baseline | 51.26 | Not recorded | 69b0f6f82d603e6de3e45c92 |

### XSA

ARC-E Accuracy: 60.65. Result ID: 69b114ce6dbb7075b95afb58.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

Recorded evaluation configuration: {"Model size":"2.7B","Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### XSA

ARC-E Accuracy: 58.84. Result ID: 69b114ce6dbb7075b95afb56.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

Recorded evaluation configuration: {"Model size":"1.3B","Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Transformer Baseline

ARC-E Accuracy: 58.59. Result ID: 69b114ce6dbb7075b95afb57.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

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

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

Recorded evaluation configuration: {"Model size":"2.7B","Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Transformer Baseline

ARC-E Accuracy: 56.19. Result ID: 69b114ce6dbb7075b95afb55.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

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

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

Recorded evaluation configuration: {"Model size":"1.3B","Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### XSA

ARC-E Accuracy: 52.69. Result ID: 69b114ce6dbb7075b95afb54.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

Recorded evaluation configuration: {"Model size":"0.7B","Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Transformer Baseline

ARC-E Accuracy: 51.26. Result ID: 69b114ce6dbb7075b95afb53.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c92.md>)

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

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

Recorded evaluation configuration: {"Model size":"0.7B","Protocol":"Zero-shot"}. This record does not assert independent reproduction.

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