Cite

Fill in the access date before citing.

Plain text

Benchmark Registry. Graduate-Level Google-Proof Q&A Diamond benchmark results. Benchmark identifier: gpqa/diamond. https://benchmarkregistry.org/benchmarks/gpqa/diamond. Accessed [YYYY-MM-DD]. Data license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Attribution: Benchmark Registry, a project of Densa Labs — https://benchmarkregistry.org/ (CC BY 4.0). Include the cited record URL and identify any changes.

BibTeX

@misc{br_gpqa_diamond,
  title = {Graduate-Level Google-Proof Q\&A Diamond benchmark results},
  publisher = {Benchmark Registry},
  url = {https://benchmarkregistry.org/benchmarks/gpqa/diamond},
  urldate = {YYYY-MM-DD},
  note = {Benchmark identifier: gpqa/diamond; data license: CC BY 4.0; access date to be filled by the reader}
}

Report an issue

Benchmark: GPQA
Evaluated by: GPQA Authors
Release date: November 20, 2023
Version: GPQA Diamond
Metric: GPQA Diamond Accuracy

Showing the selected evaluation. Show all results

Score

DeepSeek-V4-Flash (high)

87.4%

huggingface.coGPQA Diamond AccuracyReported April 24, 2026DeepSeek AIReport an issue

Cite

Fill in the access date before citing.

Plain text

Benchmark Registry. DeepSeek-V4-Flash: Graduate-Level Google-Proof Q&A Diamond, 87.4% (high). Registry No. 110001; Record No. 2ffd1d9e1ad1f58528f55b8274c82b1a1ffdee368763fc56e269b46444297c8a. https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history&result=2ffd1d9e1ad1f58528f55b8274c82b1a1ffdee368763fc56e269b46444297c8a#BR-2ffd1d9e1ad1f58528f55b8274c82b1a1ffdee368763fc56e269b46444297c8a. Accessed [YYYY-MM-DD]. Data license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Attribution: Benchmark Registry, a project of Densa Labs — https://benchmarkregistry.org/ (CC BY 4.0). Include the cited record URL and identify any changes.

BibTeX

@misc{br_2ffd1d9e1ad1f58528f55b8274c82b1a1ffdee368763fc56e269b46444297c8a,
  title = {DeepSeek-V4-Flash: Graduate-Level Google-Proof Q\&A Diamond, 87.4\% (high)},
  publisher = {Benchmark Registry},
  url = {https://benchmarkregistry.org/benchmarks/gpqa/diamond?view=history\&result=2ffd1d9e1ad1f58528f55b8274c82b1a1ffdee368763fc56e269b46444297c8a\#BR-2ffd1d9e1ad1f58528f55b8274c82b1a1ffdee368763fc56e269b46444297c8a},
  urldate = {YYYY-MM-DD},
  note = {Registry No. 110001; Record No. 2ffd1d9e1ad1f58528f55b8274c82b1a1ffdee368763fc56e269b46444297c8a; data license: CC BY 4.0; access date to be filled by the reader}
}

Permalink to this record

Badge for this model's latest reported score in the benchmark family; it may differ from this record.

Markdown

![DeepSeek-V4-Flash: Graduate-Level Google-Proof Q&A](https://benchmarkregistry.org/badge/110001/gpqa.svg)

HTML

<img src="https://benchmarkregistry.org/badge/110001/gpqa.svg" alt="DeepSeek-V4-Flash: Graduate-Level Google-Proof Q&amp;A" height="24">

110001

Results