Knowledge benchmark

# Humanity's Last Exam leaderboard

> Humanity's Last Exam results for 41 AI models, led by GPT-6 Astra at 54.8%. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/hle
- Last updated: 2026-10-10
- Title: Humanity's Last Exam Leaderboard (October 2026): Scores by Model

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 October 10, 2026

## 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](https://noometry.com/best/knowledge)
- **Introduced:** 2025
- **Size:** About 2,500 questions
- **Format:** Multiple choice and exact match
- **Unit:** Percent (random guessing ≈ 4.8%)
- **Official site:** [lastexam.ai](https://lastexam.ai)

## Top 15 models

Top models on Humanity's Last Exam

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%
16.  0204060

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## All results

Humanity's Last Exam results by model
| # | Model | Provider | Score | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://noometry.com/models/gpt-6-astra) | [OpenAI](https://noometry.com/providers/openai) | 54.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [Claude Fable 5.1](https://noometry.com/models/claude-fable-5-1) | [Anthropic](https://noometry.com/providers/anthropic) | 46.5% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 46.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [Gemini 3.8 Flash](https://noometry.com/models/gemini-3-8-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 44.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [GPT-5.4 Pro](https://noometry.com/models/gpt-5-4-pro) | [OpenAI](https://noometry.com/providers/openai) | 44.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [Muse Spark](https://noometry.com/models/muse-spark) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 40.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 7 | [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 37.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 8 | [GPT-5.4](https://noometry.com/models/gpt-5-4) | [OpenAI](https://noometry.com/providers/openai) | 36.2% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 9 | [Claude Opus 4.7](https://noometry.com/models/claude-opus-4-7) | [Anthropic](https://noometry.com/providers/anthropic) | 36.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 10 | [Claude Opus 4.6](https://noometry.com/models/claude-opus-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 34.4% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 11 | [GPT-5 Pro](https://noometry.com/models/gpt-5-pro) | [OpenAI](https://noometry.com/providers/openai) | 31.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 12 | [GPT-5.2](https://noometry.com/models/gpt-5-2) | [OpenAI](https://noometry.com/providers/openai) | 27.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 13 | [GPT-5](https://noometry.com/models/gpt-5) | [OpenAI](https://noometry.com/providers/openai) | 25.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 14 | [Claude Opus 4.5](https://noometry.com/models/claude-opus-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 25.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 15 | [Kimi K2.5](https://noometry.com/models/kimi-k2-5) | [Moonshot AI](https://noometry.com/providers/moonshot) | 24.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 16 | [GPT-5.1](https://noometry.com/models/gpt-5-1) | [OpenAI](https://noometry.com/providers/openai) | 23.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 17 | [Gemini 2.5 Pro](https://noometry.com/models/gemini-2-5-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 21.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 18 | [o3](https://noometry.com/models/o3) | [OpenAI](https://noometry.com/providers/openai) | 20.3% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 19 | [GPT-5 Mini](https://noometry.com/models/gpt-5-mini) | [OpenAI](https://noometry.com/providers/openai) | 19.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 20 | [o4-mini](https://noometry.com/models/o4-mini) | [OpenAI](https://noometry.com/providers/openai) | 18.1% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 21 | [Claude Sonnet 4.5](https://noometry.com/models/claude-sonnet-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 13.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 22 | [Gemini 2.5 Flash](https://noometry.com/models/gemini-2-5-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 12.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 23 | [Claude Opus 4.1](https://noometry.com/models/claude-opus-4-1) | [Anthropic](https://noometry.com/providers/anthropic) | 11.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 24 | [Claude Opus 4](https://noometry.com/models/claude-opus-4) | [Anthropic](https://noometry.com/providers/anthropic) | 10.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 25 | [Gemini 3.1 Flash Lite](https://noometry.com/models/gemini-3-1-flash-lite) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 8.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 26 | [GLM-4.5](https://noometry.com/models/glm-4-5) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 8.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 27 | [GLM-4.5-Air](https://noometry.com/models/glm-4-5-air) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 8.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 28 | [o1-pro](https://noometry.com/models/o1-pro) | [OpenAI](https://noometry.com/providers/openai) | 8.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 29 | [Claude 3.7 Sonnet](https://noometry.com/models/claude-3-7-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 30 | [o1](https://noometry.com/models/o1) | [OpenAI](https://noometry.com/providers/openai) | 8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 31 | [Claude Sonnet 4](https://noometry.com/models/claude-sonnet-4) | [Anthropic](https://noometry.com/providers/anthropic) | 7.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 32 | [Gemini 2.0 Flash (Feb 2025)](https://noometry.com/models/gemini-2-0-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 6.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 33 | [Llama 4 Maverick](https://noometry.com/models/llama-4-maverick) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 5.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 34 | [GPT-4.5](https://noometry.com/models/gpt-4-5) | [OpenAI](https://noometry.com/providers/openai) | 5.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 35 | [GPT-4.1](https://noometry.com/models/gpt-4-1) | [OpenAI](https://noometry.com/providers/openai) | 5.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 36 | [Gemini 1.5 Pro (May 2024)](https://noometry.com/models/gemini-1-5-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 4.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 37 | [Mistral Medium](https://noometry.com/models/mistral-medium) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 4.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 38 | [Amazon Nova Pro](https://noometry.com/models/amazon-nova-pro) | [Amazon](https://noometry.com/providers/amazon) | 4.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 39 | [Claude 3.5 Sonnet](https://noometry.com/models/claude-3-5-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 4.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 40 | [Amazon Nova Lite](https://noometry.com/models/amazon-nova-lite) | [Amazon](https://noometry.com/providers/amazon) | 3.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 41 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 2.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [GPT-6 Astra vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-6-astra)
-   [GPT-6 Astra vs Gemini 3.1 Pro Preview](https://noometry.com/compare/gemini-3-1-pro-preview-vs-gpt-6-astra)
-   [GPT-6 Astra vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-6-astra)
-   [GPT-6 Astra vs GPT-5.4 Pro](https://noometry.com/compare/gpt-5-4-pro-vs-gpt-6-astra)
-   [Claude Fable 5.1 vs Gemini 3.1 Pro Preview](https://noometry.com/compare/claude-fable-5-1-vs-gemini-3-1-pro-preview)
-   [Claude Fable 5.1 vs Gemini 3.8 Flash](https://noometry.com/compare/claude-fable-5-1-vs-gemini-3-8-flash)

## Other knowledge benchmarks

-   [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond)
-   [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified)
-   [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro)
-   [Confabulations](https://noometry.com/benchmarks/confabulations)
-   [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination)
-   [LMArena Expert](https://noometry.com/benchmarks/arena-expert)
-   [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa)
-   [ARC (AI2) Challenge](https://noometry.com/benchmarks/arc-challenge) (reference)
-   [BoolQ](https://noometry.com/benchmarks/boolq) (reference)
-   [MMLU](https://noometry.com/benchmarks/mmlu) (reference)
-   [OpenBookQA](https://noometry.com/benchmarks/openbookqa) (reference)
-   [TriviaQA](https://noometry.com/benchmarks/triviaqa) (reference)

## 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.

### Cite this page

Noometry. (2026). Humanity's Last Exam leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/hle

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/hle.md).