# Expert Question Answering on HLE

Source: [Expert Question Answering on HLE](<https://www.sota2.com/research/sota/expert-question-answering-on-hle>)

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

Data updated: 2026-06-04T10:17:14.072Z

Evaluation of model performance on the HLE dataset specifically for Expert Question Answering tasks, utilizing metrics such as Accuracy, Decision Score, and various MFG scores.

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 | Expert Question Answering |
| Dataset (including any stated split) | HLE |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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/expert-question-answering-on-hle.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Decision Score](<https://www.sota2.com/research/sota/expert-question-answering-on-hle.md?metric=Decision%20Score>): Higher is better; unit: PERCENT.

- [CR](<https://www.sota2.com/research/sota/expert-question-answering-on-hle.md?metric=CR>): Higher is better; unit: PERCENT.

- [CD](<https://www.sota2.com/research/sota/expert-question-answering-on-hle.md?metric=CD>): Higher is better; unit: PERCENT.

- [CS](<https://www.sota2.com/research/sota/expert-question-answering-on-hle.md?metric=CS>): Higher is better; unit: PERCENT.

- [MFG\*R](<https://www.sota2.com/research/sota/expert-question-answering-on-hle.md?metric=MFG*R>): Higher is better; unit: PERCENT.

- [MFG\*D](<https://www.sota2.com/research/sota/expert-question-answering-on-hle.md?metric=MFG*D>): Higher is better; unit: PERCENT.

- [MFG\*S](<https://www.sota2.com/research/sota/expert-question-answering-on-hle.md?metric=MFG*S>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| QwQ-32B | 11.2 | Not recorded | 6a210696c10484bac23f021d |
| DeepSeek-R1-8B | 6.3 | Not recorded | 6a210696c10484bac23f021d |

### QwQ-32B

Accuracy: 11.2. Result ID: 6a21509afbc373592c1d96c5.

[Reporting paper](<https://www.sota2.com/research/paper/6a210696c10484bac23f021d.md>)

Recorded evaluation configuration: {"Model Type":"Natively-trained reasoning LM","Parameters":"32B"}. This record does not assert independent reproduction.

### DeepSeek-R1-8B

Accuracy: 6.3. Result ID: 6a21509afbc373592c1d96c4.

[Reporting paper](<https://www.sota2.com/research/paper/6a210696c10484bac23f021d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Model Type":"Distilled LRM","Parameters":"8B"}. This record does not assert independent reproduction.

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