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

GeoBench

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 49 results; the table lists them all.

#ModelOrganizationResultEvidence
1

Claude Fable 5 (high)

API access
Anthropic89%–
2

Gemini 3 Flash Preview

API access
Google DeepMind88%–
3

Gemini 2.5 Pro Preview (Jun 2025)

API access
Google DeepMind86%Log or source
4

Gemini 3.8 Flash (unknown)

API access
Google DeepMind86%–
5

Muse Spark 1.3 (unknown)

API access
Meta AI86%–
6

Gemini 3.5 Flash

API access
Google DeepMind85%–
7

Claude Fable 5.1 (high)

API access
Anthropic84%–
8

Gemini 2.5 Pro Exp (Mar 2025)

API access
Google DeepMind84%Log or source
9

Gemini 3 Pro Preview

API access
Google DeepMind84%Log or source
10

Gemini 3.1 Pro Preview

API access
Google DeepMind84%–
11

Gemini 3.1 Flash-Lite

API access
Google83%–
12

Claude Opus 4.8

API access
Anthropic81%–
13

Gemini 2.5 Pro Preview (Jun 2025)

API access
Google DeepMind81%–
14

GPT-5 (medium)

API access
OpenAI81%Log or source
15

o1 (medium)

API access
OpenAI80%Log or source
16

Gemini 2.0 Pro Exp (Feb 2025)

Hosted access (no API)
Google DeepMind77.6%–
17

Gemini 2.0 Flash (Feb 2025)

API access
Google DeepMind,Google77%Log or source
18

gemini-1.5-flash-002

API access
Google DeepMind76%Log or source
19

gemini-2.5-flash-preview-05-20

API access
Google DeepMind76%Log or source
20

Claude Opus 4.5 (32k thinking)

API access
Anthropic75%–
21

Claude Sonnet 5 (high)

API access
Anthropic74%–
22

o3 (medium)

API access
OpenAI74%Log or source
23

Claude Sonnet 4.6 (32k thinking)

API access
Anthropic73%–
24

Gemini 2.5 Flash Preview (Apr 2025)

API access
Google DeepMind73%Log or source
25

GPT-5.6 Sol (high)

API access
OpenAI73%–
26

GPT-4.1

API access
OpenAI72%Log or source
27

GPT-4o (Nov 2024)

API access
OpenAI71%Log or source
28

Gemini 2.0 Flash Thinking Exp

API access
Google DeepMind,Google70%–
29

claude-3-7-sonnet-20250219

API access
Anthropic68%Log or source
30

Claude 3.7 Sonnet (15k thinking)

API access
Anthropic65%Log or source
31

gpt-4o-mini-2024-07-18

API access
OpenAI64%Log or source
32

o4-mini (high)

API access
OpenAI64%Log or source
33

o4-mini (medium)

API access
OpenAI64%Log or source
34

Qwen2.5-VL-72B-Instruct

Open weights (unrestricted)
Alibaba62%Log or source
35

Claude 3.5 Sonnet (Oct 2024)

API access
Anthropic62%Log or source
36

Grok 4.7 (unknown)

API access
xAI61%–
37

Claude Sonnet 4.5 (32k thinking)

API access
Anthropic60%–
38

o3 (high)

API access
OpenAI60%Log or source
39

grok-4.3_unknown

Hosted access (no API)
xAI56%–
40

Llama-3.2-90B-Vision-Instruct

Open weights (restricted use)
Meta AI52%Log or source
41

Llama 4 Maverick

Open weights (restricted use)
Meta AI52%Log or source
42

gemma-3-27b-it

Open weights (restricted use)
Google DeepMind52%Log or source
43

Claude Opus 4

API access
Anthropic49%Log or source
44

grok-4-0709

API access
xAI45%Log or source
45

Qwen3.8 27B

Open weights (unrestricted)
Alibaba38%–
46

Pixtral-12B-2409

Open weights (unrestricted)
Mistral AI37%Log or source
47

claude-sonnet-4-20250514

API access
Anthropic37%Log or source
48

Claude 3.5 Haiku (Oct 2024)

API access
Anthropic34%Log or source
49

claude-sonnet-4-20250514_32K

API access
Anthropic32%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