CtrlK

GenAiHub

The open directory of AI agents, LLMs, MCP servers, workflows, and tools — search, compare, and track status across platforms.

10,000+AI Tools

50+Categories

DailyUpdates

ByATMEZ AI Solutions

Explore

Browse All AI Agents LLMs MCP Servers Tools & Frameworks

Account

Sign In Create Account Submit an Agent Saved Agents

Support

How It Works FAQ Report an Issue

Company

© 2026ATMEZ AI Solutions·All rights reserved.

Built with ❤️ for the AI community|Privacy Terms

Explore Agents LLMs MCP Servers Workflows Frameworks Tools Skills News

Humanity's Last Exam Leaderboard | GenAiHub

Instruction Following & Long Context

CAIS AI Dashboard

Humanity's Last Exam

Expert-level questions across mathematics, science, and humanities, as published by the CAIS AI Dashboard.

Published source(opens in a new tab)

Metric

Accuracy

Results shown

60

Publisher

CAIS AI Dashboard

Snapshot

Fetched 2026-09-17T23:25:31.888Z

60 of 60 models

DeepSeek 3.2

DeepSeek 4 Pro

DeepSeek R1

Fa

Fable 5

Fa

Fable 5.1

Gemini 2.5 Flash

Gemini 2.5 Flash-Lite

Gemini 2.5 Pro

Gemini 2.5 Pro-Exp

Gemini 3 Flash

Gemini 3 Pro

Gemini 3.1 Flash-Lite

Gemini 3.1 Pro

Gemini 3.5 Flash

Gemini 3.7 Flash

Gemini 3.8 Flash

GLM 5.1

GLM 5.2

GLM 5.3

GPT-4o

GPT-5

GPT-5-mini

GPT-5-Nano

GPT-5.1

GPT-5.2

GPT-5.4

GPT-5.4-mini

GPT-5.4-Nano

GPT-5.5

GPT-5.6 Luna

GPT-5.6 Sol

GPT-5.6 Terra

GPT-6 Astra

Grok 4

Grok 4 Fast

Grok 4.1 Fast

Grok 4.2

Grok 4.3

Grok 4.5

Grok 4.6

Ha

Haiku 4.5

Kimi K2

Kimi K2.5

Kimi K2.6

Kimi K3

Muse Spark 1.1

Muse Spark 1.3

o1

o3

o3-mini

o4-mini

Op

Opus 4.5

Op

Opus 4.6

Op

Opus 4.7

Op

Opus 4.8

Op

Opus 5

So

Sonnet 3.7

So

Sonnet 4

So

Sonnet 4.5

So

Sonnet 4.6

60 of 60 models

Higher is better

25

50

75

100

55

Fa

Fable 5.1

54

GPT-6 Astra

53

Fa

Fable 5

51

Op

Opus 5

49

Muse Spark 1.1

46

Gemini 3.8 Flash

46

Gemini 3.1 Pro

46

Gemini 3.7 Flash

46

GPT-5.6 Sol

44

GPT-5.5

43

Muse Spark 1.3

43

Gemini 3.5 Flash

42

Op

Opus 4.8

41

GLM 5.2

41

Kimi K3

40

GPT-5.4

40

Grok 4.6

39

Grok 4.5

39

GLM 5.3

39

Op

Opus 4.7

38

Gemini 3 Pro

37

Gemini 3 Flash

36

GPT-5.6 Terra

35

Kimi K2.6

34

Op

Opus 4.6

33

Grok 4.3

32

DeepSeek 4 Pro

32

GPT-5.6 Luna

30

Grok 4.2

30

GPT-5.2

27

GPT-5.1

26

Op

Opus 4.5

26

GLM 5.1

25

Kimi K2.5

25

GPT-5

25

Grok 4

24

GPT-5.4-mini

22

DeepSeek 3.2

22

Gemini 2.5 Pro

21

Kimi K2

21

So

Sonnet 4.6

20

o3

19

GPT-5-mini

19

Gemini 2.5 Pro-Exp

19

GPT-5.4-Nano

18

Grok 4.1 Fast

18

o4-mini

18

Grok 4 Fast

17

Gemini 3.1 Flash-Lite

15

So

Sonnet 4.5

13

o3-mini

12

Gemini 2.5 Flash

10

Ha

Haiku 4.5

10

So

Sonnet 4

9

DeepSeek R1

8

GPT-5-Nano

8

So

Sonnet 3.7

8

o1

7

Gemini 2.5 Flash-Lite

3

GPT-4o

List bars visualize relative performance. Plot bars use published 0–100 scores, shrink to a 1.5rem minimum, then scroll horizontally.

Scores are published snapshots and are only comparable within the same benchmark, version, metric, and evaluation configuration.