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

DTBench

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 241 results.

#ModelOrganizationResultEvidence
1

Claude Fable 5.2 (unknown)

API access
Anthropic99.2%–
2

Claude Fable 5.2 (xhigh)

API access
Anthropic98.9%–
3

Claude Opus 5.5 (max)

API access
Anthropic98.9%–
4

Claude Fable 5 (max)

API access
Anthropic98.4%–
5

Claude Fable 5.2 (high)

API access
Anthropic98.1%–
6

Claude Fable 5.2 (low)

API access
Anthropic98.1%–
7

Claude Fable 5.2 (medium)

API access
Anthropic98.1%–
8

Claude Opus 5 (high)

API access
Anthropic97.9%–
9

Claude Opus 5 (xhigh)

API access
Anthropic97.9%–
10

Claude Fable 5.1 (unknown)

API access
Anthropic97.6%–
11

Claude Fable 5.1 (xhigh)

API access
Anthropic97.6%–
12

Claude Opus 5 (max)

API access
Anthropic97.6%–
13

Gemini 4 Argon (low)

API access
Google DeepMind97.6%–
14

Claude Fable 5 (xhigh)

API access
Anthropic97.3%–
15

Claude Opus 5.5 (xhigh)

API access
Anthropic97.3%–
16

Claude Sonnet 5.5 (max)

API access
Anthropic97.3%–
17

Gemini 4 Argon (high)

API access
Google DeepMind97.3%–
18

Gemini 4 Argon (medium)

API access
Google DeepMind97.3%–
19

GPT-6 Astra (xhigh)

API access
OpenAI97.3%–
20

GPT-6 Sol (max)

API access
OpenAI97.3%–
21

Grok 4.6 (xhigh)

API access
xAI97.3%–
22

Claude Fable 5.1 (medium)

API access
Anthropic97.1%–
23

Gemini 3.1 Pro Preview

API access
Google DeepMind97.1%–
24

GPT-6 Astra (medium)

API access
OpenAI97.1%–
25

GPT-6 Astra (unknown thinking)

API access
OpenAI97.1%–
26

Gemini 3.7 Flash (high)

API access
Google DeepMind96.8%–
27

Claude Fable 5.1 (high)

API access
Anthropic96.5%–
28

Claude Fable 5 (high)

API access
Anthropic96.5%–
29

Claude Opus 5.5 (high)

API access
Anthropic96.5%–
30

Claude Opus 5.5 (medium)

API access
Anthropic96.5%–
31

GPT-6 Astra (high)

API access
OpenAI96.5%–
32

GPT-6.1 Sol (max)

API access
OpenAI96.5%–
33

Grok 4.5 (high)

API access
xAI96.5%–
34

Muse Spark 1.3 (unknown)

API access
Meta AI96.5%–
35

Claude Sonnet 5.5 (xhigh)

API access
Anthropic96%–
36

GPT-5.5 Pro (xhigh)

API access
OpenAI96%–
37

GPT-5.5 (xhigh)

API access
OpenAI96%–
38

GPT-5.6 Sol (pro, max)

API access
OpenAI96%–
39

Grok 4.7 (xhigh)

API access
xAI96%–
40

Claude Fable 5 (medium)

API access
Anthropic95.7%–
41

GPT-5.6 Sol (xhigh)

API access
OpenAI95.7%–
42

Gemini 3.8 Flash (unknown)

API access
Google DeepMind95.7%–
43

Claude Opus 5.5 (low)

API access
Anthropic95.5%–
44

Gemini 3.1 Pro Preview

API access
Google DeepMind95.5%–
45

Gemini 3.6 Flash

API access
Google DeepMind95.5%–
46

GPT-5.6 Sol (high)

API access
OpenAI95.5%–
47

GPT-5.6 Sol (max)

API access
OpenAI95.5%–
48

GPT-5.6 Sol (medium)

API access
OpenAI95.2%–
49

Muse Wonder (unknown)

API access
Meta AI95.2%–
50

Claude Haiku 5.5 (max)

API access
Anthropic95%–
51

Claude Opus 4.8

API access
Anthropic94.9%–
52

Claude Opus 5 (medium)

API access
Anthropic94.9%–
53

Gemini 3.1 Pro Preview

API access
Google DeepMind94.9%–
54

Gemini 3.8 Flash (low)

API access
Google DeepMind94.9%–
55

Gemini 3.8 Flash (medium)

API access
Google DeepMind94.9%–
56

GPT-6 Astra (low)

API access
OpenAI94.9%–
57

Gemini 3.5 Flash

API access
Google DeepMind94.7%–
58

Gemini 3.7 Flash (medium)

API access
Google DeepMind94.7%–
59

Muse Spark 1.2 (xhigh)

API access
Meta AI94.7%–
60

Claude Opus 4.7 (max)

API access
Anthropic94.7%–
61

GPT-5.4 (xhigh)

API access
OpenAI94.4%–
62

Muse Spark 1.1 (high)

API access
Meta AI94.4%–
63

Claude Fable 5.1 (low)

API access
Anthropic94.1%–
64

Claude Sonnet 5.5 (high)

API access
Anthropic94.1%–
65

Claude Sonnet 5.5 (medium)

API access
Anthropic93.9%–
66

DeepSeek V4 Pro 0813 (unknown)

Open weights (unrestricted)
DeepSeek93.9%–
67

GPT-5.6 Sol (low)

API access
OpenAI93.9%–
68

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)93.6%–
69

Claude Sonnet 5.5 (low)

API access
Anthropic93.3%–
70

Gemini 3.7 Flash (low)

API access
Google DeepMind93.3%–
71

GPT-5.6 Terra (max)

API access
OpenAI93.3%–
72

Kimi K3.1 Pro (max)

Open weights (restricted use)
Moonshot93.3%–
73

Claude Opus 5 (low)

API access
Anthropic93.1%–
74

GPT-5.6 Terra (xhigh)

API access
OpenAI92.5%–
75

Claude Sonnet 5 (max)

API access
Anthropic92.5%–
76

Qwen3.7 Max

API access
Alibaba92.3%–
77

Qwen3.8 Max (xhigh)

API access
Alibaba92%–
78

Claude Fable 5 (low)

API access
Anthropic91.5%–
79

Claude Opus 4.6 (max)

API access
Anthropic91.2%–
80

GPT-5.6 Terra (high)

API access
OpenAI91.2%–
81

Kimi K3 (max)

Open weights (non-commercial)
Moonshot91.2%–
82

DeepSeek V4 Flash 0731 (max)

Open weights (unrestricted)
DeepSeek90.9%–
83

GPT-5.2 (xhigh)

API access
OpenAI90.9%–
84

Kimi K2.6

Open weights (unrestricted)
Moonshot90.9%–
85

DeepSeek v4 Pro (max)

Open weights (unrestricted)
DeepSeek90.7%–
86

GPT-5 (high)

API access
OpenAI90.7%–
87

grok-4.3_high

Hosted access (no API)
xAI90.7%–
88

GPT-5.1 (high)

API access
OpenAI90.1%–
89

GPT-5.6 Terra (low)

API access
OpenAI90.1%–
90

GPT-5.6 Terra (medium)

API access
OpenAI90.1%–
91

GPT-6 Luna (max)

API access
OpenAI90.1%–
92

grok-4-20

API access
xAI90.1%–
93

nemotron-3-ultra

Open weights (unrestricted)
Nvidia90.1%–
94

Claude Opus 4.5 (high)

API access
Anthropic89.9%–
95

Claude Sonnet 4.6 (max)

API access
Anthropic89.9%–
96

DeepSeek V4.1 Flash (unknown)

Open weights (unrestricted)
DeepSeek89.9%–
97

Claude Sonnet 5 (xhigh)

API access
Anthropic89.5%–
98

Gemini 3 Flash Preview

API access
Google DeepMind89.1%–
99

GPT-5.6 Luna (xhigh)

API access
OpenAI89.1%–
100

GPT-5.6 Luna (max)

API access
OpenAI88.8%–

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