# GPQA Diamond

> Graduate-level biology, chemistry and physics questions that are hard to look up.

Source: https://www.superintelligence.com.au/benchmarks/gpqa-diamond/
Data updated 2026-10-07. Benchmark data from Epoch AI (CC BY) and official leaderboards.

Best score today: 96% (+3 pts in 12 months).
Human comparison: Experts in their own field, 81%. https://arxiv.org/abs/2311.12022

## What it tests

Multiple-choice questions in biology, chemistry and physics, written by people with or working towards PhDs and checked so the answer can’t simply be searched for online.

## Why it matters

It shows whether a model can reason through graduate-level science rather than recall facts.

## Caveats

Top models now sit near the ceiling, so small differences between them mean little. Four answer options also mean a random guess scores about 25%, which is why the line never starts at zero.

## Best score by quarter

| Quarter | Best score | Record held by |
| --- | --- | --- |
| Q1 2023 | 36% | GPT-4 (Mar 2023) |
| Q2 2023 | 36% | GPT-4 (Mar 2023) |
| Q3 2023 | 36% | GPT-4 (Mar 2023) |
| Q4 2023 | 42% | GPT-4 Turbo Preview (Nov 2023) |
| Q1 2024 | 47% | claude-3-opus-20240229 |
| Q2 2024 | 54% | Claude 3.5 Sonnet (Jun 2024) |
| Q3 2024 | 62% | o1-mini (high) |
| Q4 2024 | 77% | o1 (high) |
| Q1 2025 | 84% | Gemini 2.5 Pro Exp (Mar 2025) |
| Q2 2025 | 85% | gemini-2.5-pro |
| Q3 2025 | 87% | grok-4-0709 |
| Q4 2025 | 93% | Gemini 3 Pro Preview |
| Q1 2026 | 95% | GPT-5.4 Pro (xhigh) |
| Q2 2026 | 95% | GPT-5.4 Pro (xhigh) |
| Q3 2026 | 96% | GPT-6 Astra (max) |
| Q4 2026 | 96% | GPT-6 Astra (max) |

## Top scores right now

| Rank | Model | Developer | Score | Released |
| --- | --- | --- | --- | --- |
| 1 | GPT-6 Astra (max) | OpenAI | 96% | 2026-09-03 |
| 2 | Claude Sonnet 5.5 (max) | Anthropic | 96% | 2026-09-28 |
| 3 | Gemini 3.8 Flash (high) | Google DeepMind | 95% | 2026-09-02 |
| 4 | GPT-6.1 Sol (max) | OpenAI | 95% | 2026-09-29 |
| 5 | Gemini 3.7 Flash (high) | Google DeepMind | 95% | 2026-08-13 |
| 6 | GPT-5.4 Pro (xhigh) | OpenAI | 95% | 2026-03-05 |
| 7 | Gemini 3.1 Pro Preview | Google DeepMind | 94% | 2026-02-19 |
| 8 | GPT-6 Sol (max) | OpenAI | 94% | 2026-09-22 |
| 9 | Gemini 3.6 Flash | Google DeepMind | 94% | 2026-07-21 |
| 10 | GPT-5.5 (xhigh) | OpenAI | 94% | 2026-04-23 |
| 11 | Grok 4.6 (high) | xAI | 94% | 2026-08-12 |
| 12 | GPT-5.5 Pro (xhigh) | OpenAI | 94% | 2026-04-23 |
| 13 | Claude Opus 5 (max) | Anthropic | 94% | 2026-07-24 |
| 14 | GPT-5.6 Sol (max) | OpenAI | 94% | 2026-07-09 |
| 15 | Grok 4.5 (high) | xAI | 93% | 2026-07-08 |
| 16 | GPT-5.6 Terra (max) | OpenAI | 93% | 2026-07-09 |
| 17 | GPT-5.4 (xhigh) | OpenAI | 93% | 2026-03-05 |
| 18 | Grok 4.6 (xhigh) | xAI | 93% | 2026-08-12 |
| 19 | Kimi K3 (max) | Moonshot | 93% | 2026-07-16 |
| 20 | Claude Opus 5 | Anthropic | 93% | 2026-07-24 |
| 21 | Gemini 3.5 Flash | Google DeepMind | 93% | 2026-05-19 |
| 22 | Grok 4.7 (xhigh) | xAI | 93% | 2026-09-21 |
| 23 | Qwen3.8 Max (xhigh) | Alibaba | 93% | 2026-08-02 |
| 24 | Gemini 3 Pro Preview | Google DeepMind | 93% | 2025-11-18 |
| 25 | Qwen3.8 Max (0902) (xhigh) | Alibaba | 92% | 2026-09-01 |
| 26 | Kimi K3 (high) | Moonshot | 92% | 2026-07-16 |
| 27 | GLM-5.2 | Z.ai (Zhipu AI) | 92% | 2026-06-16 |
| 28 | DeepSeek V4 Pro 0813 (max) | DeepSeek | 92% | 2026-08-13 |
| 29 | GPT-5.6 Luna (max) | OpenAI | 92% | 2026-07-09 |
| 30 | GPT-5.2 (xhigh) | OpenAI | 91% | 2025-12-11 |
| 31 | Claude Opus 4.8 | Anthropic | 91% | 2026-05-28 |
| 32 | DeepSeek V4 Flash 0731 (max) | DeepSeek | 91% | 2026-07-31 |
| 33 | DeepSeek v4 Pro (high) | DeepSeek | 91% | 2026-04-24 |
| 34 | Qwen3.7 Max | Alibaba | 91% | 2026-05-19 |
| 35 | MiniMax-M3 | MiniMax | 91% | 2026-06-01 |
| 36 | GLM-5.3 (max) | Z.ai (Zhipu AI) | 91% | 2026-08-14 |
| 37 | Kimi K2.6 | Moonshot | 91% | 2026-04-20 |
| 38 | GPT-5.5 (low) | OpenAI | 91% | 2026-04-23 |
| 39 | Claude Opus 5.5 (max) | Anthropic | 91% | 2026-09-22 |
| 40 | Claude Opus 4.6 (32k thinking) | Anthropic | 91% | 2026-02-05 |
| 41 | Claude Sonnet 5 (xhigh) | Anthropic | 91% | 2026-06-30 |
| 42 | GPT-6 Luna (max) | OpenAI | 91% | 2026-09-22 |
| 43 | Claude Opus 4.7 (xhigh) | Anthropic | 90% | 2026-04-16 |
| 44 | GLM-5.3-Flash (max) | Z.ai (Zhipu AI) | 90% | 2026-08-20 |
| 45 | GPT-5.4 (high) | OpenAI | 90% | 2026-03-05 |
| 46 | GLM-5.1 | Z.ai (Zhipu AI) | 90% | 2026-04-07 |
| 47 | GPT-5.6 Sol (low) | OpenAI | 90% | 2026-07-09 |
| 48 | Muse Spark | Meta AI | 90% | 2026-04-08 |
| 49 | DeepSeek v4 Pro (max) | DeepSeek | 90% | 2026-04-24 |
| 50 | Gemini 3 Flash Preview | Google DeepMind | 89% | 2025-12-17 |

Download all data: https://www.superintelligence.com.au/data/benchmarks.csv