# Human-level Exams on HLE text only

Source: [Human-level Exams on HLE text only](<https://www.sota2.com/research/sota/human-level-exams-on-hle-text-only>)

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

Data updated: 2026-02-26T06:03:52.146Z

Evaluation of model performance on the text-only subset of the Humanity's Last Exam (HLE) dataset, focusing on general Human-level Exams capabilities, measured by Score.

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 | Human-level Exams |
| Dataset (including any stated split) | HLE text only |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Score](<https://www.sota2.com/research/sota/human-level-exams-on-hle-text-only.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| gpt-oss-120b | 18.4 | Not recorded | 6965d1ae6343fa78c8323876 |
| GLM-4.5-Air | 10.8 | Not recorded | 6965d1ae6343fa78c8323876 |
| Solar Open | 10.5 | Not recorded | 6965d1ae6343fa78c8323876 |
| gpt-oss-120b | 7.23 | Not recorded | 6965d1ae6343fa78c8323876 |

### gpt-oss-120b

Score: 18.4. Result ID: 69968fb15698665ec4d89d4a.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1ae6343fa78c8323876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a0c.md>)

Recorded evaluation configuration: {"Number of Parameters":"117B","Optimization Level":"high"}. This record does not assert independent reproduction.

### GLM-4.5-Air

Score: 10.8. Result ID: 69968fb15698665ec4d89d4c.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1ae6343fa78c8323876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a891e209131cea83c41.md>)

Recorded evaluation configuration: {"Number of Parameters":"110B"}. This record does not assert independent reproduction.

### Solar Open

Score: 10.5. Result ID: 69968fb15698665ec4d89d49.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1ae6343fa78c8323876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1ae6343fa78c8323876.md>)

Recorded evaluation configuration: {"Number of Parameters":"102B"}. This record does not assert independent reproduction.

### gpt-oss-120b

Score: 7.23. Result ID: 69968fb15698665ec4d89d4b.

[Reporting paper](<https://www.sota2.com/research/paper/6965d1ae6343fa78c8323876.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a0c.md>)

Recorded evaluation configuration: {"Number of Parameters":"117B","Optimization Level":"medium"}. This record does not assert independent reproduction.

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