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

Terminal 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 59 results; the table lists them all.

#ModelOrganizationResultEvidence
1

GPT-5.5 (unknown thinking)

API access
OpenAI84.7%–
2

GPT-5.4 (unknown thinking)

API access
OpenAI81.8%–
3

Claude Opus 4.7 (unknown)

API access
Anthropic80.2%–
4

Gemini 3.1 Pro Preview

API access
Google DeepMind80.2%–
5

Claude Opus 4.6 (unknown thinking)

API access
Anthropic79.8%–
6

GPT-5.3 Codex

API access
OpenAI78.4%–
7

Claude Opus 4.6 (no thinking)

API access
Anthropic69.9%–
8

Gemini 3 Pro Preview

API access
Google DeepMind69.4%–
9

GPT-5.2 Codex

API access
OpenAI66.5%–
10

GPT-5.2 (unknown thinking)

API access
OpenAI64.9%–
11

GPT-5.2 (medium)

API access
OpenAI64.9%–
12

Gemini 3 Flash Preview

API access
Google DeepMind64.3%–
13

Claude Opus 4.5 (unknown thinking)

API access
Anthropic63.1%–
14

Claude Opus 4.5 (no thinking)

API access
Anthropic63.1%–
15

GPT-5.1 Codex Mini

API access
OpenAI61.6%–
16

GPT-5.1-Codex-Max

API access
OpenAI60.4%–
17

Claude Opus 4.5 (128k thinking)

API access
Anthropic59.1%–
18

GPT-5.1 Codex

API access
OpenAI57.8%–
19

grok-4-20

API access
xAI57.3%–
20

Claude Sonnet 4.6 (unknown thinking)

API access
Anthropic53.4%–
21

Claude Sonnet 4.6 (no thinking)

API access
Anthropic53.4%–
22

GLM-5

Open weights (unrestricted)
Z.ai (Zhipu AI)52.4%–
23

GPT-5 (unknown thinking)

API access
OpenAI49.6%–
24

GPT-5 (medium)

API access
OpenAI49.6%–
25

GPT-5.1 (medium)

API access
OpenAI47.6%–
26

GPT-5.1 (unknown thinking)

API access
OpenAI47.6%–
27

Claude Sonnet 4.5 (unknown thinking)

API access
Anthropic46.5%–
28

MiniMax-M2.7

Open weights (non-commercial)
MiniMax45.1%–
29

GPT-5-codex

API access
OpenAI44.3%–
30

Kimi K2.5

Open weights (unrestricted)
Moonshot43.2%–
31

Claude Sonnet 4.5 (no thinking)

API access
Anthropic42.8%–
32

MiniMax-M2.5

Open weights (unrestricted)
MiniMax42.7%–
33

DeepSeek-V3.2 (Thinking; Novita)

Open weights (unrestricted)
DeepSeek39.6%–
34

claude-opus-4-1-20250805

API access
Anthropic38%–
35

Claude Opus 4.1 (unknown thinking)

API access
Anthropic38%–
36

MiniMax-M2.1

Open weights (restricted use)
MiniMax36.6%–
37

Kimi K2 Thinking

Open weights (restricted use)
Moonshot35.7%–
38

Claude Haiku 4.5 (unknown thinking)

API access
Anthropic35.5%–
39

GPT-5 mini (unknown thinking)

API access
OpenAI34.8%–
40

GLM-4.7

Open weights (unrestricted)
Z.ai (Zhipu AI)33.4%–
41

gemini-2.5-pro

API access
Google DeepMind32.6%–
42

GPT-5 mini (medium)

API access
OpenAI31.9%–
43

MiniMax-M2

Open weights (unrestricted)
MiniMax30%–
44

claude-haiku-4-5-20251001

API access
Anthropic29.8%–
45

Kimi K2 Instruct

Open weights (restricted use)
Moonshot27.8%–
46

grok-4-0709

API access
xAI27.2%–
47

Qwen3-Coder-480B-A35B-Instruct

Open weights (unrestricted)
Alibaba27.2%–
48

grok-code-fast-1

–25.8%–
49

Qwen3.6 35B-A3B

Open weights (unrestricted)
Alibaba24.6%–
50

GLM-4.6

Open weights (unrestricted)
Z.ai (Zhipu AI),Tsinghua University24.5%–
51

GPT-5 nano (unknown thinking)

API access
OpenAI21.8%–
52

gpt-oss-120b

Open weights (unrestricted)
OpenAI18.7%–
53

gpt-oss-120b (unknown thinking)

Open weights (unrestricted)
OpenAI18.7%–
54

gemini-2.5-flash-preview-09-2025

API access
Google DeepMind17.1%–
55

gemini-2.5-flash

API access
Google DeepMind17.1%–
56

GPT-5 nano (medium)

API access
OpenAI11.5%–
57

Qwen3.5 9B

Open weights (restricted use)
Alibaba9.2%–
58

gpt-oss-20b

Open weights (unrestricted)
OpenAI3.4%–
59

gpt-oss-20b

Open weights (unrestricted)
OpenAI3.4%–

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