# Expert-level Science Question Answering on GPQA diamond (Acc, #Tokens)

Source: [Expert-level Science Question Answering on GPQA diamond (Acc, #Tokens)](<https://www.sota2.com/research/sota/expert-level-science-question-answering-on-gpqa-diamond-acc-sharp-tokens>)

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

Data updated: 2026-05-12T16:03:02.493Z

Evaluation of model performance on the GPQA Diamond dataset for expert-level science question answering, reporting accuracy and output token count.

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-level Science Question Answering |
| Dataset (including any stated split) | GPQA diamond |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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-level-science-question-answering-on-gpqa-diamond-acc-sharp-tokens.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Output Tokens Count](<https://www.sota2.com/research/sota/expert-level-science-question-answering-on-gpqa-diamond-acc-sharp-tokens.md?metric=Output%20Tokens%20Count>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MUR | 47.47 | Not recorded | 68fa7a151e209131cea81092 |
| MUR | 41.92 | Not recorded | 68fa7a151e209131cea81092 |
| MUR | 32.83 | Not recorded | 68fa7a151e209131cea81092 |

### MUR

Accuracy: 47.47. Result ID: 6a034f0247f34ce924e8a33f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a151e209131cea81092.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a151e209131cea81092.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Search Strategy":"phi-Decoding"}. This record does not assert independent reproduction.

### MUR

Accuracy: 41.92. Result ID: 6a034f0247f34ce924e8a33e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a151e209131cea81092.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a151e209131cea81092.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Search Strategy":"phi-Decoding"}. This record does not assert independent reproduction.

### MUR

Accuracy: 32.83. Result ID: 6a034f0247f34ce924e8a33d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a151e209131cea81092.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a151e209131cea81092.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Search Strategy":"Guided search"}. This record does not assert independent reproduction.

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