# Question Answering on ARC-Easy (zero-shot n=200 subset)

Source: [Question Answering on ARC-Easy (zero-shot n=200 subset)](<https://www.sota2.com/research/sota/question-answering-on-arc-easy-zero-shot-n-200-subset>)

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

Data updated: 2026-05-28T07:51:35.743Z

Evaluation of model performance on a specific zero-shot subset (n=200 tasks) of the ARC-Easy dataset for Question Answering, 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 | Question Answering |
| Dataset (including any stated split) | ARC-Easy zero-shot n=200/task |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/question-answering-on-arc-easy-zero-shot-n-200-subset.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| fp16 | 71 | Not recorded | 6a17cc21dbd7150506f8132a |
| HQMQ s192 r6 + Med3x | 70 | Not recorded | 6a17cc21dbd7150506f8132a |
| HQMQ s24 r6 + Med3x | 69 | Not recorded | 6a17cc21dbd7150506f8132a |
| HQMQ s96 r6 + Med3x | 67 | Not recorded | 6a17cc21dbd7150506f8132a |
| naive int4 | 24 | Not recorded | 6a17cc21dbd7150506f8132a |

### fp16

Accuracy: 71. Result ID: 6a17f318fbc373592c116a43.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

Recorded evaluation configuration: {"bits":"16.00"}. This record does not assert independent reproduction.

### HQMQ s192 r6 + Med3x

Accuracy: 70. Result ID: 6a17f318fbc373592c116a47.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

Recorded evaluation configuration: {"bits":"5.15"}. This record does not assert independent reproduction.

### HQMQ s24 r6 + Med3x

Accuracy: 69. Result ID: 6a17f318fbc373592c116a45.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

Recorded evaluation configuration: {"bits":"4.42"}. This record does not assert independent reproduction.

### HQMQ s96 r6 + Med3x

Accuracy: 67. Result ID: 6a17f318fbc373592c116a46.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

Recorded evaluation configuration: {"bits":"4.91"}. This record does not assert independent reproduction.

### naive int4

Accuracy: 24. Result ID: 6a17f318fbc373592c116a44.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc21dbd7150506f8132a.md>)

Recorded evaluation configuration: {"bits":"4.00"}. This record does not assert independent reproduction.

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