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

GSM8K

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 93 results; the table lists them all.

#ModelOrganizationResultEvidence
1

DeepSeek-Coder-V2-Instruct

Open weights (restricted use)
DeepSeek94.5%–
2

Qwen2.5-Coder-14B-Instruct

–94.2%–
3

Qwen2.5-Coder-32B-Instruct

Open weights (unrestricted)
Alibaba93%–
4

GPT-4 (Mar 2023)

API access
OpenAI92%–
5

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

API access
OpenAI91.3%–
6

Qwen2.5-Coder-32B

Open weights (unrestricted)
Alibaba91.1%–
7

GPT-4 (Jun 2023)

API access
OpenAI90%–
8

Phi-3.5-MoE-instruct

Open weights (unrestricted)
Microsoft88.7%–
9

Qwen2.5-Coder-14B

–88.7%–
10

DeepSeek-Coder-V2-Lite-Instruct

–87.6%–
11

Qwen2.5-Coder-7B-Instruct

Open weights (unrestricted)
Alibaba86.7%–
12

claude-instant-1.2

API access
Anthropic86.7%Log or source
13

Phi-3.5-mini-instruct

Open weights (unrestricted)
Microsoft86.2%–
14

DeepSeek-Coder-V2-Base

Open weights (restricted use)
DeepSeek85.8%–
15

gemma-2-9b

Open weights (restricted use)
Google DeepMind84.9%–
16

Mistral-Nemo-Base-2407

Open weights (unrestricted)
Mistral AI84.2%–
17

Qwen2.5-Coder-7B

Open weights (unrestricted)
Alibaba83.9%–
18

Llama-3.1-8B-Instruct

Open weights (restricted use)
Meta AI82.4%–
19

Gemini 1.5 Flash (May 2024)

API access
Google DeepMind82.4%–
20

claude-instant-1.1

API access
Anthropic80.9%Log or source
21

Qwen2.5-Coder-3B-Instruct

–80.7%–
22

Qwen2.5-Coder-3B

–75.7%–
23

Mixtral-8x7B-v0.1

Open weights (unrestricted)
Mistral AI74.4%–
24

Yi-34B-Chat

Open weights (restricted use)
01.AI71.7%–
25

StableBeluga2

Open weights (non-commercial)
Stability AI69.6%Log or source
26

Yi-34B

Open weights (restricted use)
01.AI67.2%–
27

DeepSeek-Coder-V2-Lite-Base

–67.1%–
28

Qwen2.5-Coder-1.5B

Open weights (unrestricted)
Alibaba65.8%–
29

internlm-20b

–62.9%–
30

Qwen-14B

Open weights (restricted use)
Alibaba60.1%–
31

Qwen-14B-Chat

Open weights (restricted use)
Alibaba59.5%–
32

starcoder2-15b

Open weights (restricted use)
Hugging Face,ServiceNow,Nvidia,BigCode57.7%–
33

code-davinci-002

API access
OpenAI56.8%Log or source
34

PaLM 540B

Unreleased
Google Research56.5%–
35

falcon-180B

Open weights (restricted use)
Technology Innovation Institute54.4%–
36

Falcon 2-11B

Open weights (restricted use)
Technology Innovation Institute53.8%–
37

Baichuan-2-13B-Base

Open weights (restricted use)
Baichuan52.8%–
38

Qwen-7B

Open weights (restricted use)
Alibaba51.7%–
39

text-davinci-003

OpenAI50.6%Log or source
40

Llama-2-70b-hf

Open weights (restricted use)
Meta AI48.4%Log or source
41

Llama-2-70b-chat

Open weights (restricted use)
Meta AI47.1%–
42

GPT-3.5 Turbo (June 2023)

API access
OpenAI46.9%Log or source
43

LLaMA-65B

Open weights (non-commercial)
Meta AI46.6%Log or source
44

gemma-7b

Open weights (restricted use)
Google DeepMind46.4%–
45

Nemotron-4 15B

Unreleased
Nvidia46%–
46

Baichuan2-13B-Chat

–45.7%–
47

Llama-2-34b

Unreleased
Meta AI42.2%–
48

text-davinci-002

API access
OpenAI41.5%Log or source
49

INTELLECT-1-Instruct

Prime Intellect,Hugging Face,Arcee AI38.6%Log or source
50

Yi-6B-Chat

Open weights (restricted use)
01.AI38.4%–
51

Mistral-7B-v0.1

Open weights (unrestricted)
Mistral AI38.1%Log or source
52

CodeQwen1.5-7B

–37.7%–
53

Llama-2-13b-chat

Open weights (restricted use)
Meta AI36.9%–
54

Mistral-7B-Instruct-v0.2

Open weights (unrestricted)
Mistral AI35.4%–
55

deepseek-coder-33b-base

Open weights (restricted use)
DeepSeek,Peking University35.4%–
56

Qwen2.5-Coder-0.5B

–34.5%–
57

mpt-30b-instruct

Open weights (unrestricted)
MosaicML34.4%Log or source
58

falcon-40b-instruct

Open weights (unrestricted)
Technology Innovation Institute33.8%Log or source
59

PaLM 62B

–33%–
60

starcoder2-7b

Open weights (restricted use)
Hugging Face,ServiceNow,Nvidia,BigCode32.7%–
61

Yi-6B

Open weights (restricted use)
01.AI32.5%–
62

LLaMA-33B

Open weights (non-commercial)
Meta AI32%Log or source
63

internlm-7b

–31.2%Log or source
64

chatglm2-6b

–28.9%–
65

vicuna-13b-v1.1

–28.1%–
66

Baichuan-13B-Base

Open weights (restricted use)
Baichuan26.8%–
67

falcon-40b

Open weights (unrestricted)
Technology Innovation Institute25%Log or source
68

Baichuan-2-7B-Base

Open weights (restricted use)
Baichuan24.5%–
69

Llama-2-13b

Open weights (restricted use)
Meta AI24.5%Log or source
70

vicuna-13b-v1.3

Open weights (restricted use)
Large Model Systems Organization,University of California (UC) Berkeley22.6%Log or source
71

starcoder2-3b

Open weights (restricted use)
Hugging Face,ServiceNow,Nvidia,BigCode21.6%–
72

deepseek-coder-6.7b-base

Open weights (restricted use)
DeepSeek,Peking University21.3%–
73

Qwen-1.8B

–21.2%Log or source
74

gemma-2b

Open weights (restricted use)
Google DeepMind17.7%–
75

mpt-30b

Open weights (unrestricted)
MosaicML16.4%Log or source
76

internlm-chat-20b

–15.7%–
77

LLaMA-13B

Open weights (non-commercial)
Meta AI15.4%Log or source
78

Llama-2-7b

Open weights (restricted use)
Meta AI14.6%–
79

bloom

Open weights (restricted use)
Hugging Face,BigScience9.5%Log or source
80

Baichuan-7B

Open weights (non-commercial)
Baichuan9.2%–
81

davinci

API access
OpenAI9%Log or source
82

mpt-7b

Open weights (unrestricted)
MosaicML8.6%–
83

LLaMA-7B

Open weights (non-commercial)
Meta AI8%Log or source
84

deepseek-coder-1.3b-base

Open weights (restricted use)
DeepSeek,Peking University4.4%–
85

falcon-7b

Open weights (unrestricted)
Technology Innovation Institute4%Log or source
86

opt-175b

Open weights (non-commercial)
Meta AI4%Log or source
87

opt-66b

Open weights (non-commercial)
Meta AI1.8%Log or source
88

curie

OpenAI1.6%Log or source
89

babbage

OpenAI0.7%Log or source
90

ada

OpenAI0.6%Log or source
91

text-curie-001

API access
OpenAI0.6%Log or source
92

text-ada-001

OpenAI0.4%Log or source
93

text-babbage-001

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