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

MirrorCode

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 of 46 results; the table lists them all.

#ModelOrganizationResultEvidence
1

Claude Sonnet 5.5 (max)

API access
Anthropic97.8% ± 1.5%Log or source
2

Claude Opus 5.5 (max)

API access
Anthropic95.6% ± 2.6%–
3

Claude Fable 5.1 (max)

API access
Anthropic93.3% ± 3.9%Log or source
4

Claude Opus 5 (max)

API access
Anthropic87.8% ± 7.2%Log or source
5

Claude Opus 5.5 (high)

API access
Anthropic78.9% ± 7.9%–
6

Claude Haiku 5.5 (max)

API access
Anthropic78.9% ± 8%Log or source
7

GPT-6.1 Terra (max)

API access
OpenAI76.7% ± 9.3%–
8

Claude Fable 5.1 (high)

API access
Anthropic73.3% ± 9.2%–
9

Claude Fable 5 (max)

API access
Anthropic70% ± 10.4%–
10

Claude Opus 4.8

API access
Anthropic65.6% ± 10.8%Log or source
11

DeepSeek V4.1 Flash (max)

Open weights (unrestricted)
DeepSeek64.4% ± 11.4%–
12

Claude Fable 5 (high)

API access
Anthropic63.9% ± 10.4%–
13

Claude Sonnet 5 (max)

API access
Anthropic63.3% ± 10.7%–
14

GPT-6.1 Sol (max)

API access
OpenAI61.1% ± 11.3%Log or source
15

GPT-6 Astra (max)

API access
OpenAI60% ± 11.8%Log or source
16

Gemini 4 Argon (high)

API access
Google DeepMind58.9% ± 11.7%Log or source
17

Grok 4.7 (xhigh)

API access
xAI54.4% ± 11.4%–
18

Kimi K3 (max)

Open weights (non-commercial)
Moonshot54.4% ± 11.4%Log or source
19

Muse Spark 1.3 (max)

API access
Meta AI54.4% ± 10.8%–
20

Qwen3.8 Max (xhigh)

API access
Alibaba52.2% ± 10.9%Log or source
21

GPT-6 Sol (max)

API access
OpenAI48.9% ± 11.2%–
22

Qwen3.8 Max (0902) (xhigh)

API access
Alibaba47.8% ± 10.3%Log or source
23

GPT-6 Astra (high)

API access
OpenAI46.7% ± 11.9%–
24

Muse Wonder (max)

API access
Meta AI45.6% ± 10.6%Log or source
25

Claude Opus 4.7 (max)

API access
Anthropic43.3% ± 9.6%–
26

Gemini 3.7 Flash (high)

API access
Google DeepMind41.1% ± 12.2%Log or source
27

GPT-5.6 Terra (max)

API access
OpenAI41.1% ± 12.4%Log or source
28

Grok 4.6 (xhigh)

API access
xAI41.1% ± 11%Log or source
29

Mistral Large 4 Preview (high)

Open weights (restricted use)
Mistral AI40% ± 10.6%–
30

Gemini 3.8 Flash (high)

API access
Google DeepMind38.9% ± 11.9%Log or source
31

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)36.7% ± 11.5%–
32

Claude Opus 4.6 (max)

API access
Anthropic33.3% ± 10%Log or source
33

DeepSeek V4 Pro 0813 (max)

Open weights (unrestricted)
DeepSeek33.3% ± 10%Log or source
34

GPT-5.2 (xhigh)

API access
OpenAI32.2% ± 10%–
35

Grok 4.5 (high)

API access
xAI32.2% ± 10.7%Log or source
36

Claude Opus 4.7 (high)

API access
Anthropic31.1% ± 9%–
37

GPT-6 Luna (max)

API access
OpenAI26.7% ± 9%Log or source
38

Gemini 3.6 Flash

API access
Google DeepMind23.3% ± 9.3%–
39

GPT-5.4 (xhigh)

API access
OpenAI23.3% ± 8.1%–
40

GPT-5.5 (xhigh)

API access
OpenAI23.3% ± 10.1%–
41

GPT-5.6 Luna (max)

API access
OpenAI21.1% ± 9.8%–
42

GPT-5.6 Sol (high)

API access
OpenAI20% ± 9.2%–
43

GPT-5.4 (high)

API access
OpenAI15.6% ± 7.7%–
44

GPT-5.5 (high)

API access
OpenAI10% ± 6%–
45

Gemini 3.1 Pro Preview

API access
Google DeepMind8.9% ± 4.6%–
46

GPT-5 (high)

API access
OpenAI4.4% ± 3.4%Log or source

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