AI vs Puzzles

Back to Home
Puzzle#1735

Wordle

Released: 2026-03-20

7
Models Tested
0
Solved
6.00
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
b
l
a
s
t
p
a
u
s
e
h
a
i
l
s
d
a
i
s
y
m
a
s
o
n

openai/gpt-4o

openai

Failed

c
r
a
n
e
s
t
a
l
l
a
b
u
s
e
m
a
s
k
s
b
a
s
s
y
b
a
s
i
s

meta-llama/llama-3.3-70b-instruct

meta

Failed

h
o
u
s
e
b
o
i
l
s
c
o
i
l
s
m
o
i
s
t
s
o
i
l
s
c
o
i
n
s

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
l
a
t
h
e
b
a
k
e
d
w
a
c
k
y
m
a
p
l
e
b
a
d
g
e

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
p
l
a
t
e
a
b
a
c
k
a
p
a
r
t
a
d
a
g
e
a
l
e
r
t

x-ai/grok-3-mini-beta

x-ai

Failed

c
r
a
n
e
d
a
i
l
y
s
a
h
i
b
m
a
x
i
s
w
a
i
t
s
k
a
k
i
s

anthropic/claude-3.7-sonnet

anthropic

Failed

s
t
a
r
e
p
s
a
l
m
s
a
u
c
y
w
a
x
e
d
b
a
s
i
c
b
a
s
i
n

Methodology Note

Each model receives the same prompt structure with Wordle rules and feedback format. Models are given a maximum of 6 attempts with standard positional feedback after each guess to help refine their next attempt.

Leaderboard