STEM & Reasoning Benchmark

GPQA Diamond (with tools)

GPQA Diamond (with tools) - Google-Proof Q&A benchmark for graduate-level scientific reasoning with tool use variant.

Category

STEM & Reasoning

Score type

percent

Scale

relative

higher is better

Models tested

1

What is GPQA Diamond (with tools)?

GPQA (Google-Proof Q&A) is a graduate-level science question set created by domain experts. Questions are written so that simply searching the web does not help: 'google-proof' means that even human experts with full search access only answer about a third of them correctly in the non-expert setting.

What does it test?

GPQA Diamond (with tools) measures hard reasoning in science, technology, engineering and math. In detail, it checks:

  • deep science knowledge beyond common exam questions
  • step-by-step scientific reasoning
  • robustness against attractive wrong answers
  • 'closed-book' problem solving without external help

How to read the score

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Frequently asked questions

What is the GPQA Diamond (with tools) benchmark?

GPQA (Google-Proof Q&A) is a graduate-level science question set created by domain experts. Questions are written so that simply searching the web does not help: 'google-proof' means that even human experts with full search access only answer about a third of them correctly in the non-expert setting.

What does GPQA Diamond (with tools) test?

GPQA Diamond (with tools) mainly measures hard reasoning in science, technology, engineering and math. Concretely, it checks: deep science knowledge beyond common exam questions; step-by-step scientific reasoning; robustness against attractive wrong answers.

How is the GPQA Diamond (with tools) score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Where do I get GPQA Diamond (with tools) data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/gpqa-diamond-with-tools/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 1 model tested

Reset
# Model Score Date Source Verified
1 GPT-OSS-20B
OpenAI
74.2%
05.08.2025 Report Verified

What now?

You've seen how models score on GPQA Diamond (with tools) — here's what to do next.