Hemmingway Download

Model card

Hemmingway-1

Hemmingway-1 is our own 27B parameter model. It writes like a person, not a machine, and it is built for talking to people and for writing beautifully. In our tests it sounds more human than any model we put next to it, at a fraction of their size.

Benchmarks

Hemmingway-1 next to the biggest models there are. Higher is better.

EQ-Bench 4 Emotional Intelligence
ModelScore
Hemmingway-11330
Fable 51341
Kimi K31332
GPT-5.51316
Opus 4.71312
Opus 4.81285
CommunicationBench Everyday Writing, Texting and Emails
ModelScore
Hemmingway-11026
Fable 5.11024
Fable 51009
GLM-5.31007
Kimi K3996
GPT-6 Astra976
Qwen3.8 27B base954
Human-Likeness Sounds Like a Person (CommunicationBench)
ModelScore
Hemmingway-11032
Fable 5.11006
GLM-5.3996
Fable 5992
Kimi K3985
GPT-6 Astra964
Qwen3.8 27B base952
StoryBench Creative Writing
ModelScore
Hemmingway-11197
Fable 5 Max1277
GLM-5.31254
Kimi K31197
Qwen3.8 Max1081
DeepSeek V4 Pro1054
Qwen3.8 27B base693

Hemmingway-1Other models

EQ-Bench 4 is a public benchmark. CommunicationBench, Human-Likeness and StoryBench are ours, marked internal.

Parameters
27 billion
Made by
Hemmingway
Built for
Talking to people and writing
Thinking
On, at its highest level unless you ask for less
Longest reply
32,768 tokens, thinking included
Tools
Function calling, in OpenAI's format
API
hemmingway-27b, OpenAI-compatible
API price
$0.24 in, $0.024 cached in, $0.90 out, per million tokens.
Where
The Hemmingway app on Mac, Windows and the web, and the API

More on Hemmingway-1

How we ran EQ-Bench 4, what changed from Qwen3.8-27B, how to run it on your own hardware, and how it compares with ChatGPT and Claude.

Use Hemmingway-1

In the Hemmingway app, or through the API.