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

FrontierMath-Tiers-1-3-v2-Private

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 125 results.

#ModelOrganizationResultEvidence
1

Claude Fable 5.2 (max)

API access
Anthropic95.1% ± 1.3%–
2

GPT-6 Astra (max)

API access
OpenAI93.7% ± 1.4%–
3

GPT-6.1 Sol (max)

API access
OpenAI93.7% ± 1.4%–
4

Claude Opus 5.5 (max)

API access
Anthropic91.2% ± 1.7%–
5

GPT-6.1 Terra (max)

API access
OpenAI90.9% ± 1.7%–
6

Gemini 4 Carbon (high)

API access
Google DeepMind90.5% ± 1.7%–
7

Claude Fable 5.1 (max)

API access
Anthropic90.2% ± 1.8%–
8

GPT-6 Sol (max)

API access
OpenAI89.8% ± 1.8%–
9

GPT-5.6 Sol (max)

API access
OpenAI89.1% ± 1.8%Log or source
10

Claude Sonnet 5.5 (max)

API access
Anthropic88.8% ± 1.9%–
11

GPT-5.5 Pro (xhigh)

API access
OpenAI87.7% ± 1.9%–
12

Claude Fable 5 (max)

API access
Anthropic87% ± 2%Log or source
13

Gemini 4 Argon (high)

API access
Google DeepMind86% ± 2.1%–
14

GPT-5.6 Terra (max)

API access
OpenAI86% ± 2.1%Log or source
15

Claude Opus 5 (max)

API access
Anthropic85.6% ± 2.1%Log or source
16

GPT-5.5 (xhigh)

API access
OpenAI85.3% ± 2.1%–
17

GPT-5.4 Pro (xhigh)

API access
OpenAI82.5% ± 2.3%Log or source
18

GPT-5.6 Luna (max)

API access
OpenAI82.1% ± 2.3%Log or source
19

Muse Wonder (max)

API access
Meta AI82.1% ± 2.3%–
20

Claude Opus 4.8

API access
Anthropic80% ± 2.4%Log or source
21

GPT-6 Luna (max)

API access
OpenAI78.9% ± 2.4%–
22

GPT-5.4 (xhigh)

API access
OpenAI78.6% ± 2.4%Log or source
23

Kimi K3.1 Pro (Together, max)

Open weights (restricted use)
Moonshot78.2% ± 2.4%–
24

Claude Haiku 5.5 (max)

API access
Anthropic75.1% ± 2.6%–
25

Qwen3.8 Max (xhigh)

API access
Alibaba74.7% ± 2.6%Log or source
26

Muse Spark 1.3 (xhigh)

API access
Meta AI74.4% ± 2.6%–
27

Muse Spark 1.3 (max)

API access
Meta AI74% ± 2.6%–
28

GPT-5.2 Pro

API access
OpenAI74% ± 2.6%–
29

Kimi K3 (max)

Open weights (non-commercial)
Moonshot72.2% ± 2.7%–
30

Gemini 3.7 Flash (high)

API access
Google DeepMind71.6% ± 2.7%Log or source
31

DeepSeek V4.1 Flash 1017 (max)

Open weights (unrestricted)
DeepSeek71.2% ± 2.7%–
32

Claude Opus 4.7 (max)

API access
Anthropic70.2% ± 2.7%Log or source
33

Muse Spark Open (xhigh)

Open weights (restricted use)
Meta AI69.8% ± 2.7%–
34

GLM-5.3 (max)

Open weights (restricted use)
Z.ai (Zhipu AI)68.8% ± 2.7%–
35

Gemini 3.8 Flash (high)

API access
Google DeepMind68.4% ± 2.8%–
36

GPT-5.2 (xhigh)

API access
OpenAI67.4% ± 2.8%–
37

DeepSeek V4.1 Flash (max)

Open weights (unrestricted)
DeepSeek67.4% ± 2.8%–
38

Claude Opus 4.6 (max)

API access
Anthropic66% ± 2.8%Log or source
39

Grok 4.6 (xhigh)

API access
xAI66% ± 2.8%Log or source
40

Claude Sonnet 5 (max)

API access
Anthropic65.6% ± 2.8%Log or source
41

Qwen3.8 Max (0902) (xhigh)

API access
Alibaba65.6% ± 2.8%–
42

DeepSeek V4 Pro 0813 (max)

Open weights (unrestricted)
DeepSeek64.6% ± 2.8%Log or source
43

Qwen3.7 Max

API access
Alibaba64.6% ± 2.8%Log or source
44

Gemini 3.5 Flash

API access
Google DeepMind62.8% ± 2.9%Log or source
45

Gemini 3.1 Pro Preview

API access
Google DeepMind59.6% ± 2.9%Log or source
46

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)59.2% ± 3%–
47

Gemini 3.6 Flash

API access
Google DeepMind58.9% ± 2.9%Log or source
48

Mistral Large 4 Preview (high)

Open weights (restricted use)
Mistral AI58.6% ± 2.9%–
49

DeepSeek V4 Flash 0731 (max)

Open weights (unrestricted)
DeepSeek57.5% ± 2.9%Log or source
50

Grok 4.5 (high)

API access
xAI57.2% ± 2.9%–
51

Kimi K2.6

Open weights (unrestricted)
Moonshot57.2% ± 2.9%Log or source
52

GLM-5.3-Flash (max)

Open weights (unrestricted)
Z.ai (Zhipu AI)55.8% ± 2.9%–
53

GPT-5 Pro

API access
OpenAI55.8% ± 2.9%Log or source
54

GPT-5 (high)

API access
OpenAI55.4% ± 2.9%–
55

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)54.7% ± 3%Log or source
56

Kimi K2.7 Code

Open weights (unrestricted)
Moonshot54% ± 3%Log or source
57

Grok 4.7 (xhigh)

API access
xAI53% ± 3%–
58

Gemini 3 Flash Preview

API access
Google DeepMind51.2% ± 3%Log or source
59

GPT-5.4 mini (xhigh)

API access
OpenAI51.2% ± 3%–
60

GPT-5 mini (high)

API access
OpenAI46.7% ± 3%Log or source
61

Inkling Small (xhigh)

Open weights (unrestricted)
Thinking Machines46.3% ± 3%Log or source
62

DeepSeek v4 Pro (max)

Open weights (unrestricted)
DeepSeek45.3% ± 3%Log or source
63

GPT-5.4 nano (high)

API access
OpenAI44.9% ± 3%Log or source
64

grok-4.20-0309-reasoning

API access
xAI44.9% ± 3%Log or source
65

grok-4.3_high

Hosted access (no API)
xAI42.8% ± 2.9%Log or source
66

GLM-5.2

Open weights (unrestricted)
Z.ai (Zhipu AI)42.5% ± 2.9%Log or source
67

GPT-5.6 Luna (low)

API access
OpenAI41.4% ± 2.9%Log or source
68

GPT-5.6 Luna (none)

API access
OpenAI39.6% ± 2.9%Log or source
69

Qwen 3.6 Plus (2026-04-02)

API access
Alibaba38.2% ± 2.9%Log or source
70

GPT-5 (low)

API access
OpenAI37.2% ± 2.9%Log or source
71

GLM-5.1

Open weights (unrestricted)
Z.ai (Zhipu AI)36.8% ± 2.9%Log or source
72

o4-mini (high)

API access
OpenAI36.1% ± 2.9%Log or source
73

Qwen3.6 27B

Open weights (unrestricted)
Alibaba35.1% ± 2.8%Log or source
74

Claude Opus 4.5 (32k thinking)

API access
Anthropic34.4% ± 2.8%Log or source
75

Qwen3.7 Plus

API access
Alibaba34.4% ± 2.8%Log or source
76

Qwen3.6 27B

Open weights (unrestricted)
Alibaba34% ± 2.8%Log or source
77

Inkling (xhigh)

Open weights (unrestricted)
Thinking Machines33.3% ± 2.8%Log or source
78

o3 (high)

API access
OpenAI33.3% ± 2.8%Log or source
79

Qwen 3.6 Plus (2026-04-02)

API access
Alibaba32.3% ± 2.8%Log or source
80

Qwen3.5 397B-A17B

Open weights (unrestricted)
Alibaba31.2% ± 2.7%Log or source
81

o3 (medium)

API access
OpenAI29.8% ± 2.7%Log or source
82

Qwen3.5 397B-A17B

Open weights (unrestricted)
Alibaba29.5% ± 2.7%Log or source
83

o4-mini (medium)

API access
OpenAI28.8% ± 2.7%Log or source
84

Gemini 3.1 Flash-Lite

API access
Google27.7% ± 2.7%Log or source
85

GPT-5.5 Instant

API access
OpenAI26.3% ± 2.6%Log or source
86

Gemini 3.5 Flash-Lite

API access
Google DeepMind26% ± 2.6%Log or source
87

glm-5.1_none

Open weights (unrestricted)
Z.ai (Zhipu AI)24.9% ± 2.6%Log or source
88

gemini-2.5-pro

API access
Google DeepMind24.6% ± 2.6%Log or source
89

GPT-5.4 mini (low)

API access
OpenAI24.6% ± 2.6%Log or source
90

Claude Sonnet 4.5 (32k thinking)

API access
Anthropic23.9% ± 2.5%Log or source
91

Gemini 3.1 Flash-Lite

API access
Google22.5% ± 2.5%Log or source
92

Qwen 3.6 Flash (2026-04-16)

Alibaba22.5% ± 2.5%Log or source
93

Gemini 3.1 Flash-Lite

API access
Google21.4% ± 2.4%Log or source
94

GPT-5.4 nano (low)

API access
OpenAI20.4% ± 2.4%Log or source
95

Qwen3.6 35B-A3B

Open weights (unrestricted)
Alibaba20.4% ± 2.4%Log or source
96

GPT-5 nano (high)

API access
OpenAI20% ± 2.4%Log or source
97

o3 (low)

API access
OpenAI19.3% ± 2.3%Log or source
98

Qwen3.7 Flash

API access
Alibaba19.3% ± 2.3%Log or source
99

Qwen3.7 Flash

API access
Alibaba19.3% ± 2.3%Log or source
100

Qwen3-Max-Instruct

API access
Alibaba18.9% ± 2.3%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