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

GSO-Bench

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 42 results; the table lists them all.

#ModelOrganizationResultEvidence
1

Claude Fable 5.1 (unknown)

API access
Anthropic88.2%–
2

GPT-6 Astra (unknown thinking)

API access
OpenAI79.4%–
3

Claude Fable 5 (unknown)

API access
Anthropic78.4%–
4

GPT-5.6 Sol (unknown thinking)

API access
OpenAI76.5%–
5

Claude Opus 4.8

API access
Anthropic47.1%–
6

Claude Opus 4.7 (no thinking)

API access
Anthropic44.1%–
7

Claude Opus 4.7 (high)

API access
Anthropic44.1%–
8

Claude Opus 4.6 (high)

API access
Anthropic41.2%–
9

GPT-5.5 (xhigh)

API access
OpenAI40.2%–
10

Claude Sonnet 5 (unknown thinking)

API access
Anthropic37.3%–
11

Claude Opus 4.6 (no thinking)

API access
Anthropic33.3%–
12

Claude Opus 4.6 (unknown thinking)

API access
Anthropic33.3%–
13

GPT-5.4 (xhigh)

API access
OpenAI31.4%–
14

GPT-5.2 (high)

API access
OpenAI27.5%–
15

Claude Opus 4.5 (no thinking)

API access
Anthropic26.5%Log or source
16

Claude Opus 4.5 (unknown thinking)

API access
Anthropic26.5%–
17

GPT-5.4 (high)

API access
OpenAI25.5%–
18

Gemini 3.1 Pro Preview

API access
Google DeepMind22.6%–
19

Gemini 3 Pro Preview

API access
Google DeepMind18.6%Log or source
20

Claude Sonnet 4.5 (unknown thinking)

API access
Anthropic14.7%–
21

Claude Sonnet 4.5 (no thinking)

API access
Anthropic14.7%Log or source
22

GPT-5.1 (unknown thinking)

API access
OpenAI13.7%–
23

GPT-5.1 (high)

API access
OpenAI13.7%–
24

Gemini 3 Flash Preview

API access
Google DeepMind9.8%–
25

o3 (high)

API access
OpenAI8.8%Log or source
26

Claude Opus 4

API access
Anthropic6.9%Log or source
27

Claude Opus 4

API access
Anthropic6.9%–
28

GPT-5 (high)

API access
OpenAI6.9%Log or source
29

Kimi K2 Instruct

Open weights (restricted use)
Moonshot4.9%Log or source
30

Qwen3-Coder-480B-A35B-Instruct

Open weights (unrestricted)
Alibaba4.9%Log or source
31

claude-sonnet-4-20250514

API access
Anthropic4.9%Log or source
32

Claude Sonnet 4 (unknown thinking)

API access
Anthropic4.9%–
33

Claude 3.5 Sonnet (Oct 2024)

API access
Anthropic4.6%Log or source
34

gemini-2.5-pro

API access
Google DeepMind3.9%Log or source
35

Gemini 2.5 Pro Preview (Jun 2025)

API access
Google DeepMind3.9%–
36

claude-3-7-sonnet-20250219

API access
Anthropic3.8%Log or source
37

Claude 3.7 Sonnet (unknown thinking)

API access
Anthropic3.8%–
38

o4-mini (high)

API access
OpenAI3.6%Log or source
39

GLM-4.5-Air

Open weights (unrestricted)
Z.ai (Zhipu AI),Tsinghua University2.9%–
40

o3-mini (high)

API access
OpenAI1.3%Log or source
41

o3-mini-2025-01-31_low

API access
OpenAI1.3%–
42

GPT-4o (Nov 2024)

API access
OpenAI0%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