We value your privacy

We use cookies to enhance your browsing experience, serve personalized content and analyze our traffic. By clicking “Accept all” you consent to our use of cookies. Cookie Policy

More options
Skip to content
FacthoryFacthory
FacthoryFacthory
    • Workspace
    • Agent
    • Knowledge
    • Analytics
    • Office apps
    • Desktop
    All features
    What’s new
    Download
  • By work

    • Organizational Knowledge Risk & Gap Intelligence
    • Scientific Research & Experimentation
    • Autonomous Analytics & Insight Discovery
    • Workforce Readiness & Adaptive Learning
    • SOP Governance & Operational Standardization
    • Process Discovery & Continuous Optimization
    • All solutions

    By industry

    • Manufacturing
    • Automotive
    • Construction & Infrastructure
    • Real Estate
    • Public Sector
    • Life Sciences
    • All industries
  • Facthory for

    • Regulated industries
    • On-premises
    • Developers

    Discover

    • What’s new
    • Blog
    • Case studies
    • Webinars
    • Models

    Learn

    • Documentation
    • Help centre
  • Pricing
  • Download
Sign inGet started
All benchmarksIndependent evaluation · Epoch AI

ARC-AGI

Each model’s result as Epoch AI’s Benchmarking Hub publishes it, run by Epoch or collected from the source it cites. Facthory has not run them.

Data: Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks, licensed CC BY 4.0. Read on 16 Nov 2026.

The chart shows the 25 best and the table the 100 best of 287 results.

#ModelOrganizationResultEvidence
1

Claude Fable 5.2 (xhigh)

API access
Anthropic98.5%–
2

Claude Fable 5 (max)

API access
Anthropic98.5%–
3

Claude Fable 5 (xhigh)

API access
Anthropic98.5%–
4

Claude Opus 5.5 (high)

API access
Anthropic98.5%–
5

Gemini 3.8 Flash (high)

API access
Google DeepMind98.5%–
6

Gemini 4 Argon (high)

API access
Google DeepMind98.5%–
7

Gemini 4 Argon (medium)

API access
Google DeepMind98.5%–
8

Gemini 4 Carbon (medium)

API access
Google DeepMind98.5%–
9

GPT-6 Astra (high)

API access
OpenAI98.5%–
10

GPT-6 Astra (xhigh)

API access
OpenAI98.5%–
11

GPT-6.1 Sol (high)

API access
OpenAI98.5%–
12

GPT-6.1 Sol (xhigh)

API access
OpenAI98.5%–
13

Gemini 3.1 Pro Preview

API access
Google DeepMind98%Log or source
14

Claude Fable 5.1 (max)

API access
Anthropic97.5%–
15

Claude Fable 5.2 (high)

API access
Anthropic97.5%–
16

Claude Fable 5.2 (max)

API access
Anthropic97.5%–
17

Claude Fable 5.2 (medium)

API access
Anthropic97.5%–
18

Claude Opus 5.5 (max)

API access
Anthropic97.5%–
19

Claude Opus 5.5 (medium)

API access
Anthropic97.5%–
20

Claude Opus 5.5 (xhigh)

API access
Anthropic97.5%–
21

Claude Opus 5 (high)

API access
Anthropic97.5%–
22

Claude Opus 5 (max)

API access
Anthropic97.5%–
23

Gemini 3.8 Flash (medium)

API access
Google DeepMind97.5%–
24

Gemini 4 Carbon (high)

API access
Google DeepMind97.5%–
25

GPT-5.6 Sol (xhigh)

API access
OpenAI97.5%–
26

GPT-6 Astra (max)

API access
OpenAI97.5%–
27

GPT-6 Astra (medium)

API access
OpenAI97.5%–
28

GPT-5.6 Sol (high)

API access
OpenAI97%–
29

Claude Fable 5.1 (xhigh)

API access
Anthropic96.5%–
30

Claude Sonnet 5.5 (max)

API access
Anthropic96.5%–
31

Claude Sonnet 5.5 (xhigh)

API access
Anthropic96.5%–
32

GPT-5.5 Pro (high)

API access
OpenAI96.5%–
33

GPT-5.6 Sol (max)

API access
OpenAI96.5%–
34

GPT-5.6 Terra (max)

API access
OpenAI96.5%–
35

GPT-6 Astra (low)

API access
OpenAI96.5%–
36

GPT-6.1 Sol (max)

API access
OpenAI96.5%–
37

Inkling 2 Small (xhigh)

Thinking Machines96.5%–
38

Claude Fable 5.1 (high)

API access
Anthropic96%–
39

Gemini 3 Deep Think

Hosted access (no API)
Google DeepMind96%–
40

Claude Fable 5 (high)

API access
Anthropic95.5%–
41

Gemini 3.7 Flash (high)

API access
Google DeepMind95.5%–
42

GPT-6 Sol (max)

API access
OpenAI95.5%–
43

GPT-6.1 Sol (medium)

API access
OpenAI95.5%–
44

GPT-5.5 Pro (xhigh)

API access
OpenAI95%–
45

GPT-5.5 (xhigh)

API access
OpenAI95%–
46

Claude Fable 5.1 (medium)

API access
Anthropic94.5%–
47

Claude Fable 5.2 (low)

API access
Anthropic94.5%–
48

DeepSeek V4.1 Flash 1017 (high)

Open weights (unrestricted)
DeepSeek94.5%–
49

DeepSeek V4.1 Flash (max)

Open weights (unrestricted)
DeepSeek94.5%–
50

GPT-5.4 Pro (xhigh)

API access
OpenAI94.5%–
51

GPT-5.5 (high)

API access
OpenAI94.5%–
52

Kimi K3 (max)

Open weights (non-commercial)
Moonshot94.5%–
53

Claude Opus 4.6 (120k thinking)

API access
Anthropic94%–
54

GPT-5.6 Terra (xhigh)

API access
OpenAI94%–
55

GPT-5.4 (xhigh)

API access
OpenAI93.7%–
56

Claude Opus 4.7 (high)

API access
Anthropic93.5%–
57

DeepSeek V4.1 Flash 1017 (max)

Open weights (unrestricted)
DeepSeek93.5%–
58

GPT-6.1 Sol (low)

API access
OpenAI93.5%–
59

GPT-5.4 (high)

API access
OpenAI92.7%–
60

GPT-6 Sol (xhigh)

API access
OpenAI92.7%–
61

Claude Fable 5 (medium)

API access
Anthropic92.5%–
62

Claude Opus 4.8

API access
Anthropic92.5%–
63

Gemini 3.5 Flash

API access
Google DeepMind92.5%–
64

GPT-5.6 Sol (medium)

API access
OpenAI92.5%–
65

GPT-5.5 (medium)

API access
OpenAI92.2%–
66

Claude Opus 4.7 (max)

API access
Anthropic92%–
67

Claude Opus 4.8

API access
Anthropic92%–
68

Claude Sonnet 5.5 (high)

API access
Anthropic92%–
69

GPT-5.6 Terra (high)

API access
OpenAI92%–
70

Claude Opus 4.8

API access
Anthropic91.5%–
71

DeepSeek V4.1 Flash 1017 (low)

Open weights (unrestricted)
DeepSeek91.5%–
72

Gemini 3.6 Flash

API access
Google DeepMind91.2%–
73

Gemini 3.7 Flash (medium)

API access
Google DeepMind91.2%–
74

Claude Opus 4.7 (low)

API access
Anthropic91%–
75

Claude Opus 4.7 (medium)

API access
Anthropic91%–
76

GLM-5.3-Flash (max)

Open weights (unrestricted)
Z.ai (Zhipu AI)91%–
77

GPT-6 Sol (high)

API access
OpenAI91%–
78

Claude Fable 5 (low)

API access
Anthropic90.5%–
79

DeepSeek V4 Pro 0813 (low)

Open weights (unrestricted)
DeepSeek90.5%–
80

DeepSeek V4.1 Flash (low)

Open weights (unrestricted)
DeepSeek90.5%–
81

Gemini 3.8 Flash (low)

API access
Google DeepMind90.5%–
82

GPT-5.2 Pro

API access
OpenAI90.5%–
83

Grok 4.7 (high)

API access
xAI90.2%–
84

Claude Fable 5.1 (low)

API access
Anthropic90%–
85

DeepSeek V4 Pro 0813 (max)

Open weights (unrestricted)
DeepSeek90%–
86

Grok 4.7 (medium)

API access
xAI90%–
87

grok-4-20

API access
xAI89.5%–
88

Grok 4.7 (xhigh)

API access
xAI89.5%–
89

Muse Spark Open (xhigh)

Open weights (restricted use)
Meta AI89%–
90

Claude Haiku 5.5 (max)

API access
Anthropic89%–
91

DeepSeek V4 Flash 0731 (max)

Open weights (unrestricted)
DeepSeek89%–
92

Muse Spark Open (high)

Open weights (restricted use)
Meta AI88.5%–
93

Claude Opus 5.5 (low)

API access
Anthropic88.5%–
94

DeepSeek V4.1 Flash (high)

Open weights (unrestricted)
DeepSeek88.5%–
95

Claude Opus 4.8

API access
Anthropic88%–
96

GPT-5.6 Luna (max)

API access
OpenAI88%–
97

GPT-5.6 Luna (xhigh)

API access
OpenAI87.7%–
98

Claude Haiku 5.5 (xhigh)

API access
Anthropic87.5%–
99

Grok 4.6 (medium)

API access
xAI87.5%–
100

Qwen3.8 27B (xhigh)

Open weights (unrestricted)
Alibaba87.5%–

A workspace for what your organization knows, with an agent that works on it.

Product

  • All features
  • Workspace
  • Agent
  • Knowledge
  • Analytics
  • Office apps
  • Desktop
  • Download
  • Pricing

Solutions

  • Organizational Knowledge Risk & Gap Intelligence
  • Scientific Research & Experimentation
  • Autonomous Analytics & Insight Discovery
  • Workforce Readiness & Adaptive Learning
  • SOP Governance & Operational Standardization
  • Process Discovery & Continuous Optimization
  • All solutions
  • All industries

Resources

  • Blog
  • Case studies
  • Webinars
  • Documentation
  • Help centre
  • Models
  • ROI calculator

Company

  • Who we are
  • Careers
  • Press hub
  • Brand kit
  • Philosophy
  • Contact us

Join our newsletter

Product news from Facthory, by email.

​

© 2026 Facthory. All rights reserved.
  • Privacy policy
  • Cookie policy
  • Terms and conditions
  • Imprint
  • Cookie settings