SimmonsBench β€” the field
THE FIELD
How good is each model, really?
Don't trust the score. See what each model actually built.
GENERATION Β· LOCKED
Drag back for older model generations Β· coming soon
πŸ”’ LOCKED
JAN '25
JUNE '26
FILTER
Design & Visual
8 tests
SVG

Draw a pelican riding a bicycle

1
2
3
β˜…
β˜…
β˜…
pelican.svg β€” GPT-5.5
$0.081
X
SIMMONS'S PICK
Qwen 3.7
$0.047
X
Opus 4.8
$1.31
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
IMAGE

Design an event poster

1
2
3
β˜…
β˜…
β˜…
event-poster.html β€” Gemini 3.5
$0.072
X
SIMMONS'S PICK
Opus 4.8
$1.42
X
GPT-5.5
$0.12
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
VIDEO Β· AGENTIC

Make a launch video for yourself (HyperFrames)

1
2
3
β˜…
β˜…
β˜…
launch-video.html β€” Opus 4.8
$1.41
X
SIMMONS'S PICK
GPT-5.5
$0.12
X
Gemini 3.5
$0.17
X
+7 MORE MODELS BUILT THIS
see all 10 β†’
IMAGE Β· STORYBOARD

Pitch the next A24 film (+ storyboard)

1
2
3
β˜…
β˜…
β˜…
a24-film.html β€” Gemini 3.5
$0.15
X
SIMMONS'S PICK
Opus 4.8
$1.42
X
GPT-5.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
HTML

Build an interactive neural-net explainer

1
2
3
β˜…
β˜…
β˜…
educational-explainer.html β€” Opus 4.8
$1.45
X
SIMMONS'S PICK
GPT-5.5
$0.42
X
GLM 5.2
$0.26
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
CANVAS Β· MATH

Build an interactive fractal explorer

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
MOTION Β· TASTE

Build a motion graphics piece (you pick the concept)

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
DECK Β· IMAGE Β· SVG

Revive a dying brand: RadioShack

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
Building Websites
6 tests
HTML

Build a SaaS landing page

1
2
3
β˜…
β˜…
β˜…
landing.html β€” Gemini 3.5
$0.15
X
SIMMONS'S PICK
Qwen 3.7
$0.035
X
MiniMax M3
$0.017
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
HTML

Build an e-commerce store

1
2
3
β˜…
β˜…
β˜…
ecommerce.html β€” Opus 4.8
$1.47
X
SIMMONS'S PICK
GPT-5.5
$0.33
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
Two of these shipped a full live store β€” walk the real thing:
Opus 4.8 β†—Fable 5 β†—
HTML

Build an award-winning portfolio site

1
2
3
β˜…
β˜…
β˜…
portfolio-site.html β€” Opus 4.8
$1.45
X
SIMMONS'S PICK
GPT-5.5
$0.25
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
WEBSITE Β· DESIGN TASTE

Design a freelance designer's portfolio site

1
2
3
β˜…
β˜…
β˜…
designer-portfolio.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
HTML Β· 3 CONCEPTS

Design a world-class website

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
WEB DESIGN Β· TASTE

Build a world-class website (you pick the concept)

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
The build is only half the story.
SEE THE BENCHMARKS β†’
Knowledge Work
19 tests
DASHBOARD

Build a financial spend dashboard

1
2
3
β˜…
β˜…
β˜…
spend.html β€” GLM 5.2
$0.28
X
SIMMONS'S PICK
GPT-5.5
$0.28
X
Opus 4.8
$1.55
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
SLIDES

Build a sales QBR deck

1
2
3
β˜…
β˜…
β˜…
sales-qbr.html β€” Opus 4.8
$1.42
X
SIMMONS'S PICK
GPT-5.5
$0.26
X
Gemini 3.5
$0.18
X
+10 MORE MODELS BUILT THIS
see all 13 β†’
DASHBOARD

Turn raw sales data into a dashboard

1
2
3
β˜…
β˜…
β˜…
small-biz-dashboard.html β€” GLM 5.2
$0.28
X
SIMMONS'S PICK
Opus 4.8
$1.52
X
GPT-5.5
$0.25
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
DATA-VIZ

Build an interactive chart

1
2
3
β˜…
β˜…
β˜…
data-viz.html β€” MiniMax M3
$0.019
X
SIMMONS'S PICK
GPT-5.5
$0.22
X
Kimi K2.7
$0.054
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
WRITING

Write a cold outreach email

1
2
3
β˜…
β˜…
β˜…
cold-email.html β€” Opus 4.8
$1.48
X
SIMMONS'S PICK
GPT-5.5
$0.039
X
Gemini 3.5
$0.10
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
DASHBOARD Β· DATA

Build a make-vs-buy model

data Β· 731 rows
1
2
3
β˜…
β˜…
β˜…
make-vs-buy.html β€” Opus 4.8
$1.55
X
SIMMONS'S PICK
GPT-5.5
$0.23
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
DASHBOARD Β· DATA

Model 3 pricing strategies

data Β· 1,620 rows
1
2
3
β˜…
β˜…
β˜…
saas-pricing.html β€” Opus 4.8
$1.55
X
SIMMONS'S PICK
GPT-5.5
$0.25
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
REPORT Β· DATA

Synthesize survey + analytics into a report

data Β· 400 rows
1
2
3
β˜…
β˜…
β˜…
survey-synthesis.html β€” Opus 4.8
$1.48
X
SIMMONS'S PICK
GPT-5.5
$0.13
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
SLIDES

Which AI model should we adopt? (decision deck)

1
2
3
β˜…
β˜…
β˜…
ai-model-deck.html β€” Opus 4.8
$1.52
X
SIMMONS'S PICK
GPT-5.5
$0.31
X
Gemini 3.5
$0.15
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
DATA-VIZ

Find the most interesting dataset + visualize it

1
2
3
β˜…
β˜…
β˜…
find-dataset-viz.html β€” GLM 5.2
$0.28
X
SIMMONS'S PICK
Opus 4.8
$1.54
X
GPT-5.5
$0.33
X
+7 MORE MODELS BUILT THIS
see all 10 β†’
MAP Β· DATA

Build an interactive earthquake map

data Β· 1,100 rows
1
2
3
β˜…
β˜…
β˜…
earthquake-map.html β€” Opus 4.8
$1.50
X
SIMMONS'S PICK
GPT-5.5
$0.18
X
Gemini 3.5
$0.18
X
+6 MORE MODELS BUILT THIS
see all 9 β†’
CREATIVE

Write & build an interactive graphic novel (3 endings)

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
WRITING

Build a text-adventure dungeon (writing test)

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
WRITING Β· VOICE

Write a YouTube intro in the creator's voice

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
SLIDES

Build a PowerPoint on the GPT-5.6 launch

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
CREATIVE

Rebrand Spirit Airlines - full ad campaign

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
KNOWLEDGE WORK Β· COPY

Rewrite a real workshop landing page

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
RESEARCH REPORT

Research and design a report on data-center water use

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
SLIDES Β· RESEARCH

Should you buy SpaceX? Build the investment deck

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
Web Apps & Tools
5 tests
CANVAS

Build an Excalidraw clone

1
2
3
β˜…
β˜…
β˜…
excalidraw-clone.html β€” Opus 4.8
$1.47
X
SIMMONS'S PICK
GPT-5.5
$0.16
X
Gemini 3.5
$0.18
X
+10 MORE MODELS BUILT THIS
see all 13 β†’
UI Β· IMAGE

Design a mobile app UI

1
2
3
β˜…
β˜…
β˜…
mobile-app-ui.html β€” Opus 4.8
$1.46
X
SIMMONS'S PICK
GPT-5.5
$0.31
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
HTML

Build a fake desktop OS with working apps

1
2
3
β˜…
β˜…
β˜…
os-clone.html β€” GLM 5.2
$0.27
X
SIMMONS'S PICK
Kimi K2.7
$0.020
X
Opus 4.8
$1.54
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
LIVE DATA Β· FORECAST

Build a weather app with its own forecast model

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
ALGORITHM Β· AUDIO

Build an MP3-to-MIDI converter

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
Games
6 tests
WEBGL

Build a playable Minecraft clone

1
2
3
β˜…
β˜…
β˜…
world.html β€” Opus 4.8
$1.38
X
SIMMONS'S PICK
GPT-5.5
$0.14
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
WEBGL

Build an Age of Empires-style RTS

1
2
3
β˜…
β˜…
β˜…
age-of-empires.html β€” Opus 4.8
$1.45
X
SIMMONS'S PICK
GPT-5.5
$0.31
X
Gemini 3.5
$0.27
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
CANVAS

Build a playable Breakout arcade game

1
2
3
β˜…
β˜…
β˜…
arcade-game.html β€” GPT-5.5
$0.42
X
SIMMONS'S PICK
Qwen 3.7
$0.020
X
Opus 4.8
$1.39
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
GAME Β· GRAPHICS

Build a great-looking racing game

1
2
3
β˜…
β˜…
β˜…
racing-game.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
GAME

Build a 2D fighting game

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
GAME Β· TASTE

Build a playable game (you pick the concept)

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
Want to put two models head to head?
OPEN THE COMPARISON β†’
3D & Simulation
9 tests
CANVAS

Build a physics sandbox

1
2
3
β˜…
β˜…
β˜…
sandbox.html β€” Opus 4.8
$1.47
X
SIMMONS'S PICK
GPT-5.5
$0.11
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
CANVAS

Build a solar system

1
2
3
β˜…
β˜…
β˜…
solar.html β€” Opus 4.8
$1.56
X
SIMMONS'S PICK
GPT-5.5
$0.19
X
Gemini 3.5
$0.17
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
WEBGL Β· AGENTIC

Build a 3D art museum

1
2
3
β˜…
β˜…
β˜…
art-museum.html β€” Opus 4.8
$1.55
X
SIMMONS'S PICK
GPT-5.5
$0.35
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
3D Β· WEBGL

Build a 3D nebula galaxy scene

1
2
3
β˜…
β˜…
β˜…
nebula-particles.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
3D Β· PROCEDURAL

Build an endless low-poly terrain flyover

1
2
3
β˜…
β˜…
β˜…
terrain-flyover.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
SIM Β· FLUID

Animate liquid sloshing in a sphere

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
3D Β· INTERACTIVE

Build an interactive 3D command-center gadget

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
3D Β· PRODUCT PAGE

Build a luxury watch product page (3D)

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
3D Β· REAL-TIME

Build a real-time 3D experience (you pick the concept)

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
Writing
9 tests
WRITING

Write and typeset a 600-word article

1
2
3
β˜…
β˜…
β˜…
article.html β€” Opus 4.8
$1.41
X
SIMMONS'S PICK
GPT-5.5
$0.067
X
Gemini 3.5
$0.075
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
WRITING

Write a viral tweet thread

1
2
3
β˜…
β˜…
β˜…
tweet-thread.html β€” Opus 4.8
$1.35
X
SIMMONS'S PICK
GPT-5.5
$0.094
X
Gemini 3.5
$0.18
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
WRITING

Write a viral LinkedIn post

1
2
3
β˜…
β˜…
β˜…
write-linkedin.html β€” Opus 4.8
$1.44
X
SIMMONS'S PICK
GPT-5.5
$0.068
X
Gemini 3.5
$0.14
X
+8 MORE MODELS BUILT THIS
see all 11 β†’
WRITING Β· LONG-FORM

Finish a year-old essay

1
2
3
β˜…
β˜…
β˜…
essay-closeout.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
WRITING Β· EXPLAINER

Explain how an AI model works

1
2
3
β˜…
β˜…
β˜…
explainer.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
WRITING Β· SOCIAL

Write a LinkedIn post (to a system prompt)

1
2
3
β˜…
β˜…
β˜…
linkedin-sonnet5.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
WRITING Β· VOICE-MATCH

Write a YouTube intro in a creator's voice

1
2
3
β˜…
β˜…
β˜…
youtube-intro.html β€” Opus 4.8
$0.060
X
SIMMONS'S PICK
Sonnet 5
$0.0000
X
Sonnet 4.6
$0.0000
X
+0 MORE MODELS BUILT THIS
see all 3 β†’
WRITING Β· HALLUCINATION TEST

Write an Isaacson-style biography intro

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
WRITING Β· AI VIDEO

Write + shot-list a 30-second Tarantino trailer

1
2
3
β˜…
β˜…
β˜…
+0 MORE MODELS BUILT THIS
see all 0 β†’
ai-for-mortals β€” subscribe
β–ͺ AI FOR MORTALS Β· THE DAILY AI EMAIL
Get this in your inbox, every day.
SimmonsBench is part of AI for Mortals, the daily email that makes AI make sense for normal people. Every new model, built and benchmarked, lands there first.