GPQA (Diamond)
Graduate-Level Google-Proof Q&A (GPQA) Diamond is a challenging benchmark of expert-level questions in biology, physics, and chemistry. Questions are designed to be answerable by domain experts but extremely difficult for non-experts, even with web search.
Metrics
Accuracy (%) on expert-level science questions
Created By
David Rein et al.
Paper
View paper →Website
Visit website →Top Model Scores
| Rank | Model | Score | Date |
|---|---|---|---|
| 1 | GPT-5.2 | 94.7% | 2026-03 |
| 2 | Claude Opus 4.6 | 93.2% | 2026-02 |
| 3 | Gemini 3 Ultra | 91.8% | 2026-01 |
| 4 | Grok 4 | 89.5% | 2026-02 |
| 5 | DeepSeek V3 | 87.1% | 2026-01 |
Related Reasoning Benchmarks
ARC (AI2 Reasoning Challenge)
The AI2 Reasoning Challenge contains 7,787 genuine grade-school science questions, split into Easy and Challenge sets. The Challenge set contains only questions that are answered incorrectly by both a retrieval-based algorithm and a word co-occurrence algorithm.
Top: GPT-5.2 — 98.2%
BBH (BIG-Bench Hard)
BIG-Bench Hard is a suite of 23 challenging tasks from the BIG-Bench benchmark where language models previously performed below average human raters. Tasks include boolean expressions, causal judgement, date understanding, disambiguation, and more.
Top: GPT-5.2 — 95.3%
DROP
Discrete Reasoning Over Paragraphs tests reading comprehension that requires discrete reasoning steps including addition, subtraction, counting, sorting, and other operations over text passages.
Top: GPT-5.2 — 93.1
ZebraLogic
ZebraLogic tests logical deduction ability using Zebra puzzles (also known as Einstein's riddle). Models must use constraint satisfaction and logical elimination to solve grid-based logic puzzles of increasing complexity.
Top: Claude Opus 4.6 — 74.8%