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-2

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 275 results.

#ModelOrganizationResultEvidence
1

GPT-6 Astra (max)

API access
OpenAI95%–
2

Gemini 4 Carbon (medium)

API access
Google DeepMind94.2%–
3

GPT-6.1 Sol (max)

API access
OpenAI94.2%–
4

Claude Fable 5.2 (xhigh)

API access
Anthropic93.8%–
5

Claude Opus 5.5 (high)

API access
Anthropic93.3%–
6

GPT-6 Astra (xhigh)

API access
OpenAI93.3%–
7

Claude Fable 5.2 (max)

API access
Anthropic92.5%–
8

Claude Opus 5.5 (xhigh)

API access
Anthropic92.5%–
9

GPT-5.6 Sol (max)

API access
OpenAI92.5%–
10

Gemini 4 Carbon (high)

API access
Google DeepMind92.1%–
11

GPT-6 Astra (high)

API access
OpenAI92.1%–
12

GPT-6 Astra (medium)

API access
OpenAI92.1%–
13

Claude Opus 5.5 (max)

API access
Anthropic91.7%–
14

GPT-6.1 Sol (high)

API access
OpenAI91.7%–
15

GPT-6.1 Sol (xhigh)

API access
OpenAI91.7%–
16

Gemini 4 Argon (high)

API access
Google DeepMind91.3%–
17

Claude Opus 5 (max)

API access
Anthropic90.4%–
18

Claude Fable 5.2 (high)

API access
Anthropic90.4%–
19

Claude Fable 5.1 (max)

API access
Anthropic90%–
20

Claude Fable 5.1 (xhigh)

API access
Anthropic90%–
21

GPT-5.6 Sol (xhigh)

API access
OpenAI90%–
22

Claude Fable 5.2 (medium)

API access
Anthropic89.6%–
23

GPT-6 Sol (max)

API access
OpenAI89.6%–
24

Claude Fable 5 (max)

API access
Anthropic89.2%–
25

Gemini 3.8 Flash (high)

API access
Google DeepMind89.2%–
26

Claude Fable 5.1 (high)

API access
Anthropic88.8%–
27

Claude Fable 5 (xhigh)

API access
Anthropic88.3%–
28

Claude Opus 5 (high)

API access
Anthropic88.3%–
29

Claude Fable 5 (high)

API access
Anthropic87.5%–
30

Claude Opus 5.5 (medium)

API access
Anthropic87.5%–
31

Gemini 4 Argon (medium)

API access
Google DeepMind87.1%–
32

Claude Fable 5.2 (low)

API access
Anthropic86.7%–
33

GPT-6.1 Sol (medium)

API access
OpenAI86.7%–
34

Claude Fable 5.1 (medium)

API access
Anthropic86.3%–
35

GPT-5.6 Sol (high)

API access
OpenAI85.4%–
36

GPT-6 Astra (low)

API access
OpenAI85.4%–
37

GPT-5.5 (xhigh)

API access
OpenAI85%–
38

Gemini 3.7 Flash (high)

API access
Google DeepMind84.6%–
39

Gemini 3 Deep Think

Hosted access (no API)
Google DeepMind84.6%–
40

GPT-5.5 Pro (high)

API access
OpenAI84.6%–
41

GPT-5.5 Pro (xhigh)

API access
OpenAI84.2%–
42

GPT-5.6 Terra (max)

API access
OpenAI83.9%–
43

Claude Sonnet 5.5 (xhigh)

API access
Anthropic83.9%–
44

GPT-5.4 Pro (xhigh)

API access
OpenAI83.3%–
45

GPT-5.5 (high)

API access
OpenAI83.3%–
46

Gemini 3.8 Flash (medium)

API access
Google DeepMind82.9%–
47

Claude Fable 5 (medium)

API access
Anthropic82.5%–
48

Inkling 2 Small (xhigh)

Thinking Machines81.7%–
49

Claude Fable 5.1 (low)

API access
Anthropic78.3%–
50

DeepSeek V4.1 Flash 1017 (max)

Open weights (unrestricted)
DeepSeek78.1%–
51

GPT-6 Sol (xhigh)

API access
OpenAI78.1%–
52

Gemini 3.8 Flash (low)

API access
Google DeepMind77.5%–
53

Gemini 3.1 Pro Preview

API access
Google DeepMind77.1%–
54

Claude Fable 5 (low)

API access
Anthropic76.8%–
55

GPT-6.1 Sol (low)

API access
OpenAI76.7%–
56

Claude Opus 4.7 (max)

API access
Anthropic75.8%–
57

GPT-5.6 Terra (xhigh)

API access
OpenAI74.2%–
58

GPT-5.4 (xhigh)

API access
OpenAI74%–
59

DeepSeek V4.1 Flash 1017 (low)

Open weights (unrestricted)
DeepSeek73.6%–
60

DeepSeek V4.1 Flash (max)

Open weights (unrestricted)
DeepSeek72.9%–
61

Claude Opus 4.8

API access
Anthropic72.1%–
62

Gemini 3.5 Flash

API access
Google DeepMind72.1%–
63

Claude Opus 4.8

API access
Anthropic71.7%–
64

GPT-5.5 (medium)

API access
OpenAI70.4%–
65

Claude Opus 5.5 (low)

API access
Anthropic70.1%–
66

Claude Opus 4.6 (120k thinking)

API access
Anthropic69.2%–
67

GPT-6 Sol (high)

API access
OpenAI68.9%–
68

DeepSeek V4.1 Flash 1017 (high)

Open weights (unrestricted)
DeepSeek68.6%–
69

Claude Opus 4.7 (high)

API access
Anthropic68.3%–
70

Claude Opus 4.7 (medium)

API access
Anthropic67.5%–
71

DeepSeek V4.1 Flash (high)

Open weights (unrestricted)
DeepSeek67.5%–
72

GPT-5.4 (high)

API access
OpenAI67.5%–
73

Claude Sonnet 5.5 (high)

API access
Anthropic67.4%–
74

Grok 4.6 (xhigh)

API access
xAI67.1%–
75

GPT-5.6 Sol (medium)

API access
OpenAI67.1%–
76

GPT-5.6 Terra (high)

API access
OpenAI67.1%–
77

GLM-5.3-Flash (max)

Open weights (unrestricted)
Z.ai (Zhipu AI)65.8%–
78

grok-4-20

API access
xAI65.1%–
79

Grok 4.6 (high)

API access
xAI65.1%–
80

Gemini 3.7 Flash (medium)

API access
Google DeepMind63.8%–
81

Claude Opus 4.8

API access
Anthropic62.2%–
82

Claude Opus 4.7 (low)

API access
Anthropic62.1%–
83

DeepSeek V4 Flash 0731 (max)

Open weights (unrestricted)
DeepSeek61.4%–
84

Grok 4.7 (xhigh)

API access
xAI61.4%–
85

Claude Haiku 5.5 (xhigh)

API access
Anthropic61.3%–
86

DeepSeek V4 Pro 0813 (max)

Open weights (unrestricted)
DeepSeek61.3%–
87

Grok 4.6 (medium)

API access
xAI61.3%–
88

DeepSeek V4.1 Flash (low)

Open weights (unrestricted)
DeepSeek60.6%–
89

Claude Sonnet 4.6 (high)

API access
Anthropic60.4%–
90

Gemini 3.6 Flash

API access
Google DeepMind60.4%–
91

Kimi K3 (max)

Open weights (non-commercial)
Moonshot60.4%–
92

DeepSeek V4 Pro 0813 (high)

Open weights (unrestricted)
DeepSeek59.7%–
93

GPT-6 Astra (none)

API access
OpenAI59.6%–
94

GPT-5.6 Luna (max)

API access
OpenAI59.5%–
95

GPT-6 Luna (max)

API access
OpenAI59.3%–
96

Grok 4.7 (medium)

API access
xAI58.8%–
97

Grok 4.7 (high)

API access
xAI58.3%–
98

Claude Sonnet 4.6 (max)

API access
Anthropic58.3%–
99

GPT-6 Sol (medium)

API access
OpenAI57.8%–
100

Muse Spark Open (xhigh)

Open weights (restricted use)
Meta AI57.5%–

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