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

WeirdML

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 172 results.

#ModelOrganizationResultEvidence
1

GPT-6 Astra (pro, max)

API access
OpenAI93.6%–
2

GPT-6 Astra (max)

API access
OpenAI93.3%–
3

Claude Fable 5.1 (max)

API access
Anthropic92.9%–
4

GPT-6 Astra (high)

API access
OpenAI92.9%–
5

Claude Fable 5.1 (high)

API access
Anthropic92.3%–
6

Claude Fable 5 (max)

API access
Anthropic91.9%–
7

Claude Opus 5 (max)

API access
Anthropic91.8%–
8

Claude Opus 5 (high)

API access
Anthropic91.6%–
9

GPT-5.6 Sol (pro, max)

API access
OpenAI89.4%–
10

GPT-5.6 Sol (high)

API access
OpenAI88.8%–
11

Claude Fable 5 (high)

API access
Anthropic87.9%–
12

GPT-5.6 Sol (max)

API access
OpenAI87%–
13

Claude Opus 5

API access
Anthropic86.3%–
14

GPT-5.5 (xhigh)

API access
OpenAI84.9%–
15

Gemini 3.8 Flash (high)

API access
Google DeepMind84.8%–
16

GPT-5.5 (high)

API access
OpenAI83.9%–
17

Claude Opus 4.8

API access
Anthropic82.9%–
18

Kimi K3 (max)

Open weights (non-commercial)
Moonshot82.6%–
19

GPT-5.3 Codex

API access
OpenAI79.3%–
20

GPT-5.6 Terra (high)

API access
OpenAI78.3%–
21

Claude Opus 4.6 (high)

API access
Anthropic78%–
22

Claude Opus 4.6 (unknown thinking)

API access
Anthropic77.9%–
23

GPT-5.3 Codex (xhigh)

API access
OpenAI77.9%–
24

GPT-5.4 (xhigh)

API access
OpenAI77.7%Log or source
25

Claude Opus 4.7 (high)

API access
Anthropic76.4%–
26

Claude Opus 4.7 (no thinking)

API access
Anthropic76.4%–
27

Claude Opus 4.7 (unknown)

API access
Anthropic76.4%–
28

Claude Opus 4.8

API access
Anthropic76%–
29

Claude Opus 4.7 (max)

API access
Anthropic75.5%–
30

GLM-5.3 (max)

Open weights (restricted use)
Z.ai (Zhipu AI)75.4%–
31

GPT-5.2 (xhigh)

API access
OpenAI72.2%Log or source
32

Gemini 3.1 Pro Preview

API access
Google DeepMind72.1%–
33

Claude Opus 4.8

API access
Anthropic70.5%–
34

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)70.1%–
35

Gemini 3 Pro Preview

API access
Google DeepMind69.9%Log or source
36

Claude Sonnet 5 (high)

API access
Anthropic68.8%–
37

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)67.3%–
38

Grok 4.6 (high)

API access
xAI67.3%–
39

GPT-5.5 (no thinking)

API access
OpenAI67.2%–
40

DeepSeek V4 Pro 0813 (max)

Open weights (unrestricted)
DeepSeek66.2%–
41

Claude Sonnet 4.6 (medium)

API access
Anthropic66.1%–
42

Claude Opus 4.6 (no thinking)

API access
Anthropic65.9%Log or source
43

Claude Opus 4.5 (16k thinking)

API access
Anthropic63.7%Log or source
44

GPT-5.2 (medium)

API access
OpenAI63.4%Log or source
45

DeepSeek V4 Flash 0731 (max)

Open weights (unrestricted)
DeepSeek63%–
46

Gemini 3.5 Flash

API access
Google DeepMind62.6%–
47

Gemini 3 Flash Preview

API access
Google DeepMind61.6%Log or source
48

GPT-5.6 Luna (high)

API access
OpenAI60.9%–
49

GPT-5.1 (high)

API access
OpenAI60.8%Log or source
50

GPT-5 (high)

API access
OpenAI60.7%Log or source
51

GPT-5 Pro

API access
OpenAI60.4%Log or source
52

GPT-5.4 mini (high)

API access
OpenAI60.3%–
53

Muse Spark 1.2 (xhigh)

API access
Meta AI60.3%–
54

o3-pro-2025-06-10_high

API access
OpenAI58.2%Log or source
55

GPT-5.4 (none)

API access
OpenAI57.4%–
56

GPT-5.4 Pro (no thinking)

API access
OpenAI57.4%–
57

GLM-5.1

Open weights (unrestricted)
Z.ai (Zhipu AI)57.1%–
58

DeepSeek V4 Flash 0731 (high)

Open weights (unrestricted)
DeepSeek57.1%–
59

Gemini 3.6 Flash

API access
Google DeepMind56.1%–
60

Kimi K2.6

Open weights (unrestricted)
Moonshot55.9%–
61

GPT-5-codex

API access
OpenAI54.5%Log or source
62

GPT-5-codex (high)

API access
OpenAI54.5%–
63

Kimi K2.7 Code

Open weights (unrestricted)
Moonshot54.1%–
64

gemini-2.5-pro_16K

API access
Google DeepMind54%Log or source
65

GPT-5 mini (high)

API access
OpenAI52.7%Log or source
66

o4-mini (high)

API access
OpenAI52.6%Log or source
67

o3 (high)

API access
OpenAI52.4%Log or source
68

Gemma 4 31B IT

Open weights (restricted use)
Google DeepMind52.3%–
69

grok-4-20

API access
xAI52.3%–
70

Gemini 3.1 Flash-Lite

API access
Google52.2%–
71

grok-4.3_unknown

Hosted access (no API)
xAI49.9%–
72

GPT-5.2 (none)

API access
OpenAI49.6%–
73

GPT-5.2 (low)

API access
OpenAI49.6%Log or source
74

GPT-5.4 nano (high)

API access
OpenAI49.2%–
75

DeepSeek v4 Pro (max)

Open weights (unrestricted)
DeepSeek48.9%–
76

GLM-5

Open weights (unrestricted)
Z.ai (Zhipu AI)48.2%–
77

gpt-oss-120b_high

Open weights (unrestricted)
OpenAI48.2%Log or source
78

openai/gpt-oss-120b_high

Open weights (unrestricted)
OpenAI48.2%–
79

Claude Sonnet 4.5 (16k thinking)

API access
Anthropic47.7%Log or source
80

o1-preview

API access
OpenAI47.6%Log or source
81

DeepSeek-V3.2-Speciale

Open weights (unrestricted)
DeepSeek46.7%–
82

Claude Sonnet 4.5 (no thinking)

API access
Anthropic46.7%Log or source
83

DeepSeek v4 Pro (high)

Open weights (unrestricted)
DeepSeek46.5%–
84

Grok 4.5 (unknown thinking)

API access
xAI46.4%–
85

claude-sonnet-4-20250514_16K

API access
Anthropic46.1%Log or source
86

o1 (high)

API access
OpenAI46.1%Log or source
87

claude-opus-4-1-20250805_16K

API access
Anthropic45.9%Log or source
88

grok-4-0709

API access
xAI45.7%Log or source
89

DeepSeek v4 Flash (max)

Open weights (unrestricted)
DeepSeek45.6%–
90

Kimi K2.5

Open weights (unrestricted)
Moonshot45.6%Log or source
91

claude-haiku-4-5-20251001

API access
Anthropic45.4%Log or source
92

claude-haiku-4-5-20251001_16K

API access
Anthropic44.2%Log or source
93

claude-sonnet-4-20250514

API access
Anthropic43.9%Log or source
94

DeepSeek v4 Flash (high)

Open weights (unrestricted)
DeepSeek43.8%–
95

Claude Opus 4

API access
Anthropic43.7%Log or source
96

Mistral Medium 3.5

Open weights (restricted use)
Mistral AI43.7%–
97

o3-mini (high)

API access
OpenAI43.7%Log or source
98

nemotron-3-ultra

Open weights (unrestricted)
Nvidia43.5%–
99

Mercury 2

API access
Inception Labs43.2%–
100

grok-4-fast

API access
xAI42.9%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