Humanity's Last Exam
Updated
Cite
Fill in the access date before citing.
Plain text
Benchmark Registry. Humanity's Last Exam Search and Python — GPT-5.2 evaluation benchmark results. Benchmark identifier: humanitys-last-exam/search-python-gpt-5-2. https://benchmarkregistry.org/benchmarks/humanitys-last-exam/search-python-gpt-5-2. 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_humanitys_last_exam_search_python_gpt_5_2,
title = {Humanity's Last Exam Search and Python — GPT-5.2 evaluation benchmark results},
publisher = {Benchmark Registry},
url = {https://benchmarkregistry.org/benchmarks/humanitys-last-exam/search-python-gpt-5-2},
urldate = {YYYY-MM-DD},
note = {Benchmark identifier: humanitys-last-exam/search-python-gpt-5-2; data license: CC BY 4.0; access date to be filled by the reader}
}Results
1 result
| Provider | Model | Score | Source | Registry No. |
|---|---|---|---|---|
| OpenAI | GPT-5.2 (xhigh) | 45.5% | openai.com for GPT-5.2 (xhigh) on Humanity's Last Exam Search and Python — GPT-5.2 evaluation (opens in a new tab)Humanity's Last Exam AccuracyReported Launch postOpenAISelf-reportedRecord for GPT-5.2 on Humanity's Last Exam Search and Python — GPT-5.2 evaluation | 10012 |