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

APEX-Agents

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 65 results; the table lists them all.

#ModelOrganizationResultEvidence
1

Gemini 4 Carbon (unknown)

API access
Google DeepMind84.2%–
2

Gemini 4 Argon (unknown)

API access
Google DeepMind82.4%–
3

Claude Fable 5.2 (unknown)

API access
Anthropic80.1%–
4

Claude Sonnet 5.5 (max)

API access
Anthropic75.5%–
5

Claude Opus 5.5 (max)

API access
Anthropic73.5%–
6

DeepSeek V4.1 Flash 1017 (max)

Open weights (unrestricted)
DeepSeek69.8%–
7

Claude Fable 5.1 (unknown)

API access
Anthropic68.6%–
8

GPT-6.1 Terra (max)

API access
OpenAI68.3%–
9

Gemini 3.7 Flash (unknown)

API access
Google DeepMind67.8%–
10

Muse Wonder (max)

API access
Meta AI66.1%–
11

Claude Opus 5 (max)

API access
Anthropic65.8%–
12

Kimi K3.1 Pro (unknown)

Open weights (restricted use)
Moonshot65.5%–
13

Grok 4.6 (unknown)

API access
xAI65.3%–
14

GPT-6 Astra (unknown thinking)

API access
OpenAI64.7%–
15

Gemini 3.8 Flash (unknown)

API access
Google DeepMind64.3%–
16

Muse Ember (unknown)

API access
Meta AI64.3%–
17

Claude Fable 5

API access
Anthropic63.6%–
18

Qwen3.8 Max (unknown)

API access
Alibaba63.3%–
19

GPT-6.1 Sol (max)

API access
OpenAI60%–
20

Claude Fable 5.1 (high)

API access
Anthropic59.7%–
21

Muse Spark 1.3 (unknown)

API access
Meta AI58.6%–
22

GPT-5.6 Terra (max)

API access
OpenAI58.2%–
23

GLM-5.3 (unknown thinking)

Open weights (restricted use)
Z.ai (Zhipu AI)56.6%–
24

Grok 4.5 (unknown thinking)

API access
xAI56.2%–
25

Claude Haiku 5.5 (max)

API access
Anthropic56.1%–
26

GPT-5.5 (unknown thinking)

API access
OpenAI55.1%–
27

Grok 4.7 (unknown)

API access
xAI54.6%–
28

Claude Sonnet 5 (unknown thinking)

API access
Anthropic54.5%–
29

MiMo-V2.6 Pro

Xiaomi Corp54.4%–
30

GPT-6 Sol (max)

API access
OpenAI54.3%–
31

GLM-5.3-Flash (unknown)

Open weights (unrestricted)
Z.ai (Zhipu AI)52.8%–
32

Claude Opus 5.5 (medium)

API access
Anthropic52.5%–
33

GPT-5.4 (unknown thinking)

API access
OpenAI52.4%–
34

Mistral Large 4 Preview (high)

Open weights (restricted use)
Mistral AI51.6%–
35

GPT-5.6 Sol (pro, max)

API access
OpenAI51.4%–
36

Claude Opus 4.7 (max)

API access
Anthropic49.2%–
37

Claude Opus 4.8

API access
Anthropic48.9%–
38

Beam 1.0 (max)

Open weights (unrestricted)
Reflection48.8%–
39

Kimi K3 (unknown)

Open weights (non-commercial)
Moonshot47.8%–
40

Muse Spark 1.3 (max)

API access
Meta AI47.6%–
41

Qwen3.8 27B

Open weights (unrestricted)
Alibaba47.5%–
42

DeepSeek V4 Pro 0813 (unknown)

Open weights (unrestricted)
DeepSeek47.3%–
43

Gemini 3.6 Flash

API access
Google DeepMind46.9%–
44

Inkling 2 Small (unknown)

Thinking Machines46.8%–
45

Claude Opus 4.6 (max)

API access
Anthropic46.3%–
46

Muse Spark 1.2

API access
Meta AI45.4%–
47

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)45.2%–
48

Claude Sonnet 5.5 (medium)

API access
Anthropic44.6%–
49

GPT-6 Luna (max)

API access
OpenAI44.3%–
50

Claude Sonnet 4.6 (high)

API access
Anthropic43%–
51

GPT-5.6 Luna (unknown thinking)

API access
OpenAI43%–
52

GLM-5.1

Open weights (unrestricted)
Z.ai (Zhipu AI)40.9%–
53

DeepSeek V4.1 Flash (unknown)

Open weights (unrestricted)
DeepSeek39.5%–
54

MiniMax-M3

Open weights (restricted use)
MiniMax37.7%–
55

Kimi K2.7 Code

Open weights (unrestricted)
Moonshot37.6%–
56

Gemini 3.1 Pro Preview

API access
Google DeepMind35.1%–
57

Inkling

Open weights (unrestricted)
Thinking Machines33.8%–
58

Muse Spark Open (unknown)

Open weights (restricted use)
Meta AI33.4%–
59

Muse Spark 1.1

API access
Meta AI31.8%–
60

Gemini 3.5 Flash-Lite

API access
Google DeepMind29.3%–
61

Gemini 3.5 Flash

API access
Google DeepMind27.5%–
62

Qwen3.5 397B-A17B

Open weights (unrestricted)
Alibaba24.9%–
63

nemotron-3-ultra

Open weights (unrestricted)
Nvidia22.7%–
64

DeepSeek-V3.2 (Thinking; Novita)

Open weights (unrestricted)
DeepSeek21.3%–
65

gpt-oss-120b

Open weights (unrestricted)
OpenAI4.4%–

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