Noometry

Knowledge benchmark

Humanity's Last Exam leaderboard

As of October 2026, GPT-6 Astra has the highest published Humanity's Last Exam score on Noometry at 54.8%, out of 41 models with results.

Last verified

About Humanity's Last Exam

A crowd-sourced exam of expert-written questions across dozens of academic fields, designed to sit at the frontier of human knowledge.

Category
Knowledge
Introduced
2025
Size
About 2,500 questions
Format
Multiple choice and exact match
Unit
Percent (random guessing ≈ 4.8%)
Official site
lastexam.ai

Top 15 models

  1. GPT-6 Astra 54.8%
  2. Claude Fable 5.1 46.5%
  3. Gemini 3.1 Pro Preview 46.4%
  4. Gemini 3.8 Flash 44.5%
  5. GPT-5.4 Pro 44.3%
  6. Muse Spark 40.6%
  7. Gemini 3 Pro 37.5%
  8. GPT-5.4 36.2%
  9. Claude Opus 4.7 36.2%
  10. Claude Opus 4.6 34.4%
  11. GPT-5 Pro 31.6%
  12. GPT-5.2 27.8%
  13. GPT-5 25.3%
  14. Claude Opus 4.5 25.2%
  15. Kimi K2.5 24.4%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1GPT-6 Astra OpenAI54.8%Epoch AI
2Claude Fable 5.1 Anthropic46.5%xhighEpoch AI
3Gemini 3.1 Pro Preview Google46.4%Epoch AI
4Gemini 3.8 Flash Google44.5%Epoch AI
5GPT-5.4 Pro OpenAI44.3%Epoch AI
6Muse Spark Meta40.6%Epoch AI
7Gemini 3 Pro Google37.5%Epoch AI
8GPT-5.4 OpenAI36.2%xhighEpoch AI
9Claude Opus 4.7 Anthropic36.2%Epoch AI
10Claude Opus 4.6 Anthropic34.4%maxEpoch AI
11GPT-5 Pro OpenAI31.6%Epoch AI
12GPT-5.2 OpenAI27.8%Epoch AI
13GPT-5 OpenAI25.3%Epoch AI
14Claude Opus 4.5 Anthropic25.2%Epoch AI
15Kimi K2.5 Moonshot AI24.4%Epoch AI
16GPT-5.1 OpenAI23.7%Epoch AI
17Gemini 2.5 Pro Google21.6%Epoch AI
18o3 OpenAI20.3%highEpoch AI
19GPT-5 Mini OpenAI19.4%Epoch AI
20o4-mini OpenAI18.1%highEpoch AI
21Claude Sonnet 4.5 Anthropic13.7%Epoch AI
22Gemini 2.5 Flash Google12.1%Epoch AI
23Claude Opus 4.1 Anthropic11.5%Epoch AI
24Claude Opus 4 Anthropic10.7%Epoch AI
25Gemini 3.1 Flash Lite Google8.6%Epoch AI
26GLM-4.5 Z.ai (Zhipu)8.3%Epoch AI
27GLM-4.5-Air Z.ai (Zhipu)8.1%Epoch AI
28o1-pro OpenAI8.1%Epoch AI
29Claude 3.7 Sonnet Anthropic8%Epoch AI
30o1 OpenAI8%Epoch AI
31Claude Sonnet 4 Anthropic7.8%Epoch AI
32Gemini 2.0 Flash (Feb 2025) Google6.6%Epoch AI
33Llama 4 Maverick Meta5.7%Epoch AI
34GPT-4.5 OpenAI5.4%Epoch AI
35GPT-4.1 OpenAI5.4%Epoch AI
36Gemini 1.5 Pro (May 2024) Google4.6%Epoch AI
37Mistral Medium Mistral AI4.5%Epoch AI
38Amazon Nova Pro Amazon4.4%Epoch AI
39Claude 3.5 Sonnet Anthropic4.1%Epoch AI
40Amazon Nova Lite Amazon3.6%Epoch AI
41GPT-4o OpenAI2.7%Epoch AI

Compare the leaders

Other knowledge benchmarks

Frequently asked questions

What does Humanity's Last Exam measure?

A crowd-sourced exam of expert-written questions across dozens of academic fields, designed to sit at the frontier of human knowledge.

Which model has the highest Humanity's Last Exam score?

As of October 2026, GPT-6 Astra has the highest published Humanity's Last Exam score on Noometry at 54.8%, out of 41 models with results.

What is the best open-weight model on Humanity's Last Exam?

Kimi K2.5 has the highest Humanity's Last Exam accuracy among open-weight models at 24.4%, ranking 15 of 41 overall.