# GPQA Diamond

> The hardest subset of GPQA featuring the most challenging graduate-level science questions. Sometimes reported separately from the standard GPQA benchmark.

Canonical page: https://benchlm.ai/benchmarks/gpqa-diamond

- Category: [Reasoning](/reasoning)
- Last updated: September 15, 2026

## About GPQA Diamond

- Year: 2023
- Tasks: Expert-level science questions
- Format: Multiple choice questions
- Difficulty: Graduate-level scientific reasoning
- Paper: [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022)

GPQA Diamond is the 'diamond' difficulty tier of GPQA, containing the most expert-validated and challenging questions. It is often cited in system cards as a standalone benchmark for scientific reasoning.

GPQA Diamond is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (0 models)

Benchmark data for this page is coming soon.

## FAQ

### What does GPQA Diamond measure?

The hardest subset of GPQA featuring the most challenging graduate-level science questions. Sometimes reported separately from the standard GPQA benchmark.

### Which model scores highest on GPQA Diamond?

No models have been evaluated on GPQA Diamond yet.

### How many models are evaluated on GPQA Diamond?

0 AI models have been evaluated on GPQA Diamond on BenchLM.

### Does GPQA Diamond affect BenchLM's overall score?

Not directly. GPQA Diamond is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.