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

ProofBench

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 85 results; the table lists them all.

#ModelOrganizationResultEvidence
1

Claude Fable 5.1 (max)

API access
Anthropic100%–
2

Claude Fable 5.2 (max)

API access
Anthropic100%–
3

Claude Opus 5.5 (max)

API access
Anthropic100%–
4

Claude Sonnet 5.5 (max)

API access
Anthropic100%–
5

Claude Opus 5 (max)

API access
Anthropic99%–
6

Gemini 4 Argon (unknown)

API access
Google DeepMind99%–
7

GPT-6 Astra (unknown thinking)

API access
OpenAI99%–
8

GPT-6.1 Sol (unknown thinking)

API access
OpenAI99%–
9

Claude Fable 5 (max)

API access
Anthropic95%–
10

Kimi K3.1 Pro (unknown)

Open weights (restricted use)
Moonshot91%–
11

Claude Haiku 5.5 (max)

API access
Anthropic89%–
12

Kimi K3 (unknown)

Open weights (non-commercial)
Moonshot

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
87%
–
13

Muse Wonder (unknown)

API access
Meta AI84%–
14

GPT-5.6 Sol (max)

API access
OpenAI83%–
15

GPT-6 Sol (unknown thinking)

API access
OpenAI83%–
16

Claude Sonnet 5 (max)

API access
Anthropic77%–
17

Tencent Hy4 preview (unknown)

Open weights (unrestricted)
Tencent75%–
18

GPT-5.6 Terra (xhigh)

API access
OpenAI74%–
19

MiMo-V2.6 Pro

Xiaomi Corp70%–
20

Claude Opus 4.8

API access
Anthropic69%–
21

GPT-6 Luna (unknown thinking)

API access
OpenAI64%–
22

MiMo-V2.6 Flash

Xiaomi Corp63%–
23

GPT-5.6 Luna (max)

API access
OpenAI60%–
24

Gemini 3.7 Flash (unknown)

API access
Google DeepMind58%–
25

Muse Spark 1.3 (max)

API access
Meta AI58%–
26

Qwen3.8 Max (unknown)

API access
Alibaba58%–
27

DeepSeek V4 Flash 0731 (unknown)

Open weights (unrestricted)
DeepSeek56%–
28

GPT-5.4 (xhigh)

API access
OpenAI56%–
29

Muse Spark 1.3 (unknown)

API access
Meta AI55%–
30

Claude Opus 4.7 (max)

API access
Anthropic54%–
31

DeepSeek V4.1 Flash (unknown)

Open weights (unrestricted)
DeepSeek54%–
32

Grok 4.6 (unknown)

API access
xAI51%–
33

Claude Opus 4.6 (max)

API access
Anthropic50%–
34

DeepSeek V4 Pro 0813 (unknown)

Open weights (unrestricted)
DeepSeek50%–
35

GPT-5.5 (xhigh)

API access
OpenAI50%–
36

GLM-5.3 (max)

Open weights (restricted use)
Z.ai (Zhipu AI)49%–
37

Gemini 3.8 Flash (unknown)

API access
Google DeepMind48%–
38

Claude Sonnet 4.6 (max)

API access
Anthropic45%–
39

Muse Spark 1.2

API access
Meta AI43%–
40

Step 5 Preview (unknown)

API access
StepFun42%–
41

Muse Spark 1.1

API access
Meta AI39%–
42

Claude Opus 4.5 (unknown thinking)

API access
Anthropic36%–
43

Gemini 3.6 Flash

API access
Google DeepMind36%–
44

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)35%–
45

Gemini 3.5 Flash

API access
Google DeepMind31%–
46

Grok 4.5 (high)

API access
xAI31%–
47

Gemini 3.1 Pro Preview

API access
Google DeepMind26%–
48

Grok 4.7 (unknown)

API access
xAI26%–
49

Qwen3.7 Max

API access
Alibaba26%–
50

GLM-5.1

Open weights (unrestricted)
Z.ai (Zhipu AI)22.2%–
51

mimo-v2.5-pro

Open weights (unrestricted)
Xiaomi Corp22%–
52

GLM-5.3-Flash (max)

Open weights (unrestricted)
Z.ai (Zhipu AI)21%–
53

GPT-5.4 mini (xhigh)

API access
OpenAI21%–
54

Gemini 3 Pro Preview

API access
Google DeepMind20%–
55

Claude Sonnet 4.5 (unknown thinking)

API access
Anthropic19%–
56

MiniMax-M3

Open weights (restricted use)
MiniMax18%–
57

Beam 1.0 (unknown)

Open weights (unrestricted)
Reflection18%–
58

GPT-5 (high)

API access
OpenAI18%–
59

Muse Spark

API access
Meta AI17%–
60

DeepSeek v4 Pro (max)

Open weights (unrestricted)
DeepSeek16%–
61

Kimi K2.6

Open weights (unrestricted)
Moonshot16%–
62

mimo-v2.5

Open weights (unrestricted)
Xiaomi Corp16%–
63

Qwen3.8 27B

Open weights (unrestricted)
Alibaba16%–
64

Gemini 3 Flash Preview

API access
Google DeepMind15%–
65

GPT-5.2 (xhigh)

API access
OpenAI15%–
66

grok-4.20-0309-reasoning

API access
xAI14%–
67

Gemini 3.5 Flash-Lite

API access
Google DeepMind13%–
68

GPT-5 nano (high)

API access
OpenAI12%–
69

grok-4.3_high

Hosted access (no API)
xAI11%–
70

Mistral Large 4 Preview (unknown)

Open weights (restricted use)
Mistral AI10%–
71

GPT-5 mini (high)

API access
OpenAI9%–
72

GPT-5.1-Codex-Max

API access
OpenAI9%–
73

Mistral Medium 3.5

Open weights (restricted use)
Mistral AI9%–
74

DeepSeek-V3.2 (Thinking; Fireworks)

Open weights (unrestricted)
DeepSeek8%–
75

GLM-4.7

Open weights (unrestricted)
Z.ai (Zhipu AI)6%–
76

Inkling Small

Open weights (unrestricted)
Thinking Machines6%–
77

GPT-5.4 nano (high)

API access
OpenAI5%–
78

MiniMax-M2.5

Open weights (unrestricted)
MiniMax4%–
79

grok-4-1-fast-reasoning

API access
xAI4%–
80

MiniMax-M2.7

Open weights (non-commercial)
MiniMax3%–
81

Mercury 2.5 (unknown)

API access
Inception Labs3%–
82

nemotron-3-ultra

Open weights (unrestricted)
Nvidia2%–
83

Inkling

Open weights (unrestricted)
Thinking Machines0%–
84

Laguna M.1

Poolside0%–
85

Laguna XS.2

Open weights (unrestricted)
Poolside0%–