SimmonsBench — compare
COMPARE
Two models, head to head.
Pick two — their builds side by side, and where they land on every board.
VS
The builds
Same prompt, both models. 97 tests — click any build to open it.
FILTER
Opus 4.8
◉GPT-5.5
DASHBOARD · DATA
Build a make-vs-buy model
WEBGL · AGENTIC
Build a 3D art museum
WRITING · LONG-FORM
Finish a year-old essay
build.exe×
no build…
WRITING · EXPLAINER
Explain how an AI model works
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
WRITING · HALLUCINATION TEST
Write an Isaacson-style biography intro
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
KNOWLEDGE WORK · CREATIVE
Revive a dying brand: J.Crew
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
GAME · SIMULATION · ECONOMY
Build a RollerCoaster Tycoon 2 clone
build.exe×
no build…
build.exe×
no build…
WEB · FIDELITY · FIXED TARGET
Clone Mana Yerba Mate, pixel for pixel
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
WEB · FIDELITY + 3D
Clone butter.video, 3D and all
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
WEB · FIDELITY + MOTION
Clone heronaiapp.com, motion and all
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
VIDEO · MOTION + PHOTOREAL
Launch video for Clanker Coffee Co.
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
build.exe×
no build…
WEB · FIDELITY + MOTION
Shopify Editions Winter '26, rebuilt
build.exe×
no build…
build.exe×
no build…
GAME · CHARACTERS + FEEL
Backyard Baseball, playable
build.exe×
no build…
build.exe×
no build…
3D · FILM + INTERACTIVE
Central Park: a visual history
build.exe×
no build…
build.exe×
no build…
● The Field
SimmonsBench
Leaderboards
Composite · all 7 boards · scored out of 100
SimmonsBench
1
Opus 5
12.36 /100
2
Opus 4.8
12.16 /100
3
Fable 5
11.51 /100
4
GPT-5.5
10.70 /100
5
Gemini 3.5
10.66 /100
6
Grok 4.3
9.02 /100
7
GPT-5.6 Sol
7.85 /100
8
GLM 5.2
7.83 /100
9
DeepSeek V4
7.72 /100
10
Kimi K2.7
7.59 /100
11
Kimi K3
7.59 /100
12
Qwen 3.7
7.42 /100
13
Mistral Large
7.07 /100
14
MiniMax M3
6.31 /100
15
GPT-OSS 120b
5.90 /100
16
Fable 5.5
0.00 /100
17
Fable 5.1
0.00 /100
18
Sonnet 5
0.00 /100
19
Sonnet 4.6
0.00 /100
20
GPT-6 Astra
0.00 /100
21
Grok 4.7
0.00 /100
22
Grok 4.7 (Grok Build)
0.00 /100
23
Opus 5.5
0.00 /100
24
Sonnet 5.5
0.00 /100
25
Muse Wonder Full
0.00 /100
26
Gemini 4 Argon
0.00 /100
See the full ranking + how it's scored
→