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

HellaSwag

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 76 results; the table lists them all.

#ModelOrganizationResultEvidence
1

GPT-4 (Mar 2023)

API access
OpenAI95.3%–
2

gpt-4-32k-0314

API access
OpenAI95.3%–
3

Llama-3.1-405B

Open weights (restricted use)
Meta AI89.2%Log or source
4

falcon-180B

Open weights (restricted use)
Technology Innovation Institute89%–
5

DeepSeek-V3

Open weights (restricted use)
DeepSeek88.9%Log or source
6

DeepSeek-V2

Open weights (restricted use)
DeepSeek87.1%Log or source
7

PaLM 2-L

–86.8%Log or source
8

Mixtral-8x7B-v0.1

Open weights (unrestricted)
Mistral AI86.7%Log or source
9

text-davinci-003

OpenAI85.5%–
10

Llama-2-70b-hf

Open weights (restricted use)
Meta AI85.3%–
11

Qwen2.5-72B

Open weights (unrestricted)
Alibaba84.8%Log or source
12

LLaMA-65B

Open weights (non-commercial)
Meta AI84.2%Log or source
13

StableBeluga2

Open weights (non-commercial)
Stability AI84.1%–
14

PaLM 2-M

–84%Log or source
15

PaLM 540B

Unreleased
Google Research83.4%Log or source
16

Qwen2.5-Coder-32B

Open weights (unrestricted)
Alibaba83%Log or source
17

LLaMA-33B

Open weights (non-commercial)
Meta AI82.8%Log or source
18

falcon-40b

Open weights (unrestricted)
Technology Innovation Institute82.8%–
19

Megatron-Turing NLG 530B

Unreleased
Microsoft,Nvidia82.4%–
20

Nemotron-4 15B

Unreleased
Nvidia82.4%–
21

Phi-3-medium-128k-instruct

Open weights (unrestricted)
Microsoft82.4%–
22

gemma-7b

Open weights (restricted use)
Google DeepMind82.2%Log or source
23

Falcon 2-11B

Open weights (restricted use)
Technology Innovation Institute82.1%–
24

PaLM 2-S

–82%Log or source
25

text-davinci-002

API access
OpenAI81.5%Log or source
26

Mistral-7B-v0.1

Open weights (unrestricted)
Mistral AI81%Log or source
27

Llama-2-13b

Open weights (restricted use)
Meta AI80.7%Log or source
28

Qwen2.5-Coder-14B

–80.2%Log or source
29

Gopher (280B)

Unreleased
DeepMind79.2%Log or source
30

LLaMA-13B

Open weights (non-commercial)
Meta AI79.2%Log or source
31

opt-175b

Open weights (non-commercial)
Meta AI79.1%Log or source
32

text-davinci-001

API access
OpenAI78.9%Log or source
33

internlm-20b

–78.1%–
34

davinci

API access
OpenAI77.5%Log or source
35

Llama-2-7b

Open weights (restricted use)
Meta AI77.2%Log or source
36

Phi-3-small-8k-instruct

Open weights (unrestricted)
Microsoft77%–
37

Qwen2.5-Coder-7B

Open weights (unrestricted)
Alibaba76.8%Log or source
38

Phi-3-mini-4k-instruct

Open weights (unrestricted)
Microsoft76.7%–
39

GLaM (MoE)

Unreleased
Google76.6%–
40

Yi-9B

–76.4%–
41

mpt-7b

Open weights (unrestricted)
MosaicML76.4%–
42

falcon-7b

Open weights (unrestricted)
Technology Innovation Institute76.3%–
43

LLaMA-7B

Open weights (non-commercial)
Meta AI76.1%Log or source
44

opt-66b

Open weights (non-commercial)
Meta AI74.5%Log or source
45

Yi-6B

Open weights (restricted use)
01.AI74.4%–
46

bloom

Open weights (restricted use)
Hugging Face,BigScience74.4%Log or source
47

xgen-7b-8k-base

Open weights (unrestricted)
Salesforce74.2%–
48

open_llama_7b

–71.8%–
49

INTELLECT-1-Instruct

Prime Intellect,Hugging Face,Arcee AI71.4%Log or source
50

gemma-2b

Open weights (restricted use)
Google DeepMind71.4%Log or source
51

Qwen2.5-Coder-3B

–70.9%Log or source
52

Baichuan-2-13B-Base

Open weights (restricted use)
Baichuan70.8%–
53

dolly-v2-12b

Open weights (unrestricted)
Databricks70.8%–
54

internlm-7b

–70.6%–
55

gpt-neox-20b

Open weights (unrestricted)
EleutherAI70.5%–
56

RedPajama-INCITE-7B-Base

–70.3%–
57

opt-13b

–69.9%–
58

curie

OpenAI68.2%Log or source
59

Baichuan-2-7B-Base

Open weights (restricted use)
Baichuan68%–
60

text-curie-001

API access
OpenAI67.6%Log or source
61

gpt-j-6b

Open weights (unrestricted)
EleutherAI,LAION66.2%–
62

Qwen2.5-Coder-1.5B

Open weights (unrestricted)
Alibaba61.8%Log or source
63

Cerebras-GPT-13B

Open weights (unrestricted)
Cerebras Systems59.4%–
64

vicuna-13b-v1.1

–57.8%–
65

chatglm2-6b

–57%–
66

text-babbage-001

API access
OpenAI56.1%Log or source
67

babbage

OpenAI55.5%Log or source
68

phi-2

Open weights (unrestricted)
Microsoft53.6%–
69

Qwen2.5-Coder-0.5B

–48.4%Log or source
70

phi-1_5

Open weights (unrestricted)
Microsoft47.6%–
71

ada

OpenAI43.5%Log or source
72

text-ada-001

OpenAI42.9%Log or source
73

gpt-neo-2.7B

Open weights (unrestricted)
EleutherAI42.7%–
74

opt-1.3b

Open weights (non-commercial)
Meta AI41.5%–
75

stablelm-tuned-alpha-7b

–40.7%–
76

gpt2-xl

Open weights (unrestricted)
OpenAI40%–

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