# Humanity’s Last Exam

> Thousands of expert questions across 100+ subjects, chosen to stump AI.

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

Best score today: 55% (+17 pts in 12 months).
Human comparison: There is no overall human score. Each question was written by a specialist to be hard for other specialists, and no one person could answer across every field.

## What it tests

About 2,500 questions across more than 100 subjects, written by around a thousand subject experts and kept only if leading models of the time got them wrong.

## Why it matters

It was designed as a broad academic exam that AI would struggle with for years.

## Caveats

Because questions were chosen to beat older models, early scores start artificially near zero. Results come from the official leaderboard rather than Epoch AI’s own runs.

## Best score by quarter

| Quarter | Best score | Record held by |
| --- | --- | --- |
| Q3 2024 | 5% | Gemini-1.5-Pro-002 |
| Q4 2024 | 8% | o1 (unknown thinking) |
| Q1 2025 | 18% | Gemini 2.5 Pro Exp (Mar 2025) |
| Q2 2025 | 22% | Gemini 2.5 Pro Preview (Jun 2025) |
| Q3 2025 | 25% | GPT-5 (high) |
| Q4 2025 | 38% | Gemini 3 Pro Preview |
| Q1 2026 | 46% | Gemini 3.1 Pro Preview |
| Q2 2026 | 46% | Gemini 3.1 Pro Preview |
| Q3 2026 | 55% | GPT-6 Astra (unknown thinking) |
| Q4 2026 | 55% | GPT-6 Astra (unknown thinking) |

## Top scores right now

| Rank | Model | Developer | Score | Released |
| --- | --- | --- | --- | --- |
| 1 | GPT-6 Astra (unknown thinking) | OpenAI | 55% | 2026-09-03 |
| 2 | Claude Fable 5.1 (xhigh) | Anthropic | 47% | 2026-09-01 |
| 3 | Gemini 3.1 Pro Preview | Google DeepMind | 46% | 2026-02-19 |
| 4 | Gemini 3.8 Flash (unknown) | Google DeepMind | 45% | 2026-09-02 |
| 5 | GPT-5.4 Pro | OpenAI | 44% | 2026-03-05 |
| 6 | Muse Spark | Meta AI | 41% | 2026-04-08 |
| 7 | Gemini 3 Pro Preview | Google DeepMind | 38% | 2025-11-18 |
| 8 | GPT-5.4 (xhigh) | OpenAI | 36% | 2026-03-05 |
| 9 | Claude Opus 4.7 (unknown) | Anthropic | 36% | 2026-04-16 |
| 10 | Claude Opus 4.6 (max) | Anthropic | 34% | 2026-02-05 |
| 11 | GPT-5 Pro | OpenAI | 32% | 2025-10-07 |
| 12 | GPT-5.2 (unknown thinking) | OpenAI | 28% | 2025-12-11 |
| 13 | GPT-5 (high) | OpenAI | 25% | 2025-08-07 |
| 14 | GPT-5 (unknown thinking) | OpenAI | 25% | 2025-08-07 |
| 15 | Claude Opus 4.5 (unknown thinking) | Anthropic | 25% | 2025-11-24 |
| 16 | Kimi K2.5 | Moonshot | 24% | 2026-01-27 |
| 17 | GPT-5.1 (unknown thinking) | OpenAI | 24% | 2025-11-13 |
| 18 | Gemini 2.5 Pro Preview (Jun 2025) | Google DeepMind | 22% | 2025-06-05 |
| 19 | o3 (high) | OpenAI | 20% | 2025-04-16 |
| 20 | GPT-5 mini (unknown thinking) | OpenAI | 19% | 2025-08-07 |
| 21 | o3 (medium) | OpenAI | 19% | 2025-04-16 |
| 22 | Claude Opus 4.6 (no thinking) | Anthropic | 19% | 2026-02-05 |
| 23 | Gemini 2.5 Pro Exp (Mar 2025) | Google DeepMind | 18% | 2025-03-25 |
| 24 | o4-mini (high) | OpenAI | 18% | 2025-04-16 |
| 25 | o4-mini (medium) | OpenAI | 14% | 2025-04-16 |
| 26 | Claude Sonnet 4.5 (unknown thinking) | Anthropic | 14% | 2025-09-29 |
| 27 | Gemini 2.5 Flash Preview (Apr 2025) | Google DeepMind | 12% | 2025-04-17 |
| 28 | Claude Opus 4.1 (unknown thinking) | Anthropic | 12% | 2025-08-05 |
| 29 | Gemini 2.5 Flash Preview (May 2025) | Google DeepMind | 11% | 2025-05-20 |
| 30 | Claude Opus 4 | Anthropic | 11% | 2025-05-22 |
| 31 | Gemini 3.1 Flash-Lite | Google | 9% | 2026-03-03 |
| 32 | glm-4p5 | Z.ai (Zhipu AI) | 8% | 2025-08-03 |
| 33 | o1 Pro | OpenAI | 8% | 2025-03-19 |
| 34 | glm-4p5-air | Z.ai (Zhipu AI) | 8% | 2025-07-20 |
| 35 | Claude 3.7 Sonnet (unknown thinking) | Anthropic | 8% | 2025-02-24 |
| 36 | o1 (unknown thinking) | OpenAI | 8% | 2024-12-17 |
| 37 | Claude Sonnet 4 (unknown thinking) | Anthropic | 8% | 2025-05-22 |
| 38 | GPT-5.1 (no thinking) | OpenAI | 7% | 2025-11-13 |
| 39 | Gemini 2.0 Flash Thinking Exp | Google DeepMind | 7% | 2025-01-21 |
| 40 | Llama 4 Maverick | Meta AI | 6% | 2025-04-05 |
| 41 | GPT-4.5 Preview (Feb 2025) | OpenAI | 5% | 2025-02-27 |
| 42 | GPT-4.1 | OpenAI | 5% | 2025-04-14 |
| 43 | Gemini-1.5-Pro-002 | Google DeepMind | 5% | 2024-09-24 |
| 44 | Mistral Medium 3 | Mistral AI | 5% | 2025-05-07 |
| 45 | Nova Pro | Amazon | 4% | 2024-12-03 |
| 46 | Claude 3.5 Sonnet (Oct 2024) | Anthropic | 4% | 2024-10-22 |
| 47 | Nova Lite | Amazon | 4% | 2024-12-03 |
| 48 | GPT-4o (Nov 2024) | OpenAI | 3% | 2024-11-20 |

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