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

PIQA

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 60 results; the table lists them all.

#ModelOrganizationResultEvidence
1

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

API access
OpenAI88.7%–
2

Phi-3.5-MoE-instruct

Open weights (unrestricted)
Microsoft88.6%–
3

gemini-1.5-flash-002

API access
Google DeepMind87.5%–
4

Llama-3.1-405B

Open weights (restricted use)
Meta AI85.9%–
5

falcon-180B

Open weights (restricted use)
Technology Innovation Institute84.9%–
6

DeepSeek-V3-Base

Open weights (restricted use)
DeepSeek84.7%–
7

Inflection-1

Hosted access (no API)
Inflection AI84.2%–
8

DeepSeek-V2

Open weights (restricted use)
DeepSeek83.9%–
9

gemma-2-9b

Open weights (restricted use)
Google DeepMind83.7%–
10

Mixtral-8x7B-v0.1

Open weights (unrestricted)
Mistral AI83.6%–
11

Mistral-Nemo-Base-2407

Open weights (unrestricted)
Mistral AI83.5%–
12

StableBeluga2

Open weights (non-commercial)
Stability AI83.3%Log or source
13

LLaMA-65B

Open weights (non-commercial)
Meta AI82.8%Log or source
14

Llama-2-70b-hf

Open weights (restricted use)
Meta AI82.8%Log or source
15

Qwen2.5-72B

Open weights (unrestricted)
Alibaba82.6%–
16

Nemotron-4 15B

Unreleased
Nvidia82.4%–
17

falcon-40b

Open weights (unrestricted)
Technology Innovation Institute82.4%–
18

LLaMA-33B

Open weights (non-commercial)
Meta AI82.3%Log or source
19

PaLM 540B

Unreleased
Google Research82.3%–
20

Mistral-7B-Instruct-v0.1

Open weights (unrestricted)
Mistral AI82.2%–
21

Mistral-7B-Instruct-v0.2

Open weights (unrestricted)
Mistral AI82.2%–
22

Megatron-Turing NLG 530B

Unreleased
Microsoft,Nvidia82%Log or source
23

Llama-2-34b

Unreleased
Meta AI81.9%–
24

mpt-30b

Open weights (unrestricted)
MosaicML81.9%–
25

Chinchilla (70B)

Unreleased
DeepMind81.8%–
26

Gopher (280B)

Unreleased
DeepMind81.8%Log or source
27

Llama-3.1-8B-Instruct

Open weights (restricted use)
Meta AI81.2%–
28

gemma-7b

Open weights (restricted use)
Google DeepMind81.2%–
29

Phi-3.5-mini-instruct

Open weights (unrestricted)
Microsoft81%–
30

mpt-7b

Open weights (unrestricted)
MosaicML80.6%Log or source
31

Llama-2-13b

Open weights (restricted use)
Meta AI80.5%–
32

PaLM 62B

–80.5%–
33

text-davinci-001

API access
OpenAI80.4%–
34

internlm-20b

–80.3%Log or source
35

LLaMA-13B

Open weights (non-commercial)
Meta AI80.1%Log or source
36

Qwen-14B

Open weights (restricted use)
Alibaba79.9%Log or source
37

LLaMA-7B

Open weights (non-commercial)
Meta AI79.8%Log or source
38

Llama-2-7b

Open weights (restricted use)
Meta AI78.8%–
39

Baichuan-2-13B-Base

Open weights (restricted use)
Baichuan78.1%Log or source
40

Qwen-7B

Open weights (restricted use)
Alibaba77.9%Log or source
41

internlm-7b

–77.9%Log or source
42

vicuna-13b-v1.1

–77.4%–
43

gemma-2b

Open weights (restricted use)
Google DeepMind77.3%–
44

RedPajama-INCITE-7B-Base

–76.9%–
45

falcon-7b

Open weights (unrestricted)
Technology Innovation Institute76.7%Log or source
46

gpt-neox-20b

Open weights (unrestricted)
EleutherAI76.7%–
47

Baichuan-7B

Open weights (non-commercial)
Baichuan76.2%Log or source
48

open_llama_7b

–76%–
49

opt-13b

–75.7%–
50

xgen-7b-8k-base

Open weights (unrestricted)
Salesforce75.5%–
51

dolly-v2-12b

Open weights (unrestricted)
Databricks75.4%–
52

gpt-j-6b

Open weights (unrestricted)
EleutherAI,LAION75.4%–
53

Cerebras-GPT-13B

Open weights (unrestricted)
Cerebras Systems73.5%–
54

Mistral-7B-v0.1

Open weights (unrestricted)
Mistral AI73.4%–
55

Qwen-1.8B

–73.3%Log or source
56

gpt-neo-2.7B

Open weights (unrestricted)
EleutherAI72.9%–
57

gpt2-xl

Open weights (unrestricted)
OpenAI70.5%–
58

chatglm2-6b

–69.6%Log or source
59

opt-1.3b

Open weights (non-commercial)
Meta AI69%–
60

stablelm-tuned-alpha-7b

–65.8%–

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