AI vs Puzzles

Back to Home
Puzzle#1769

Wordle

Released: 2026-04-23

7
Models Tested
2
Solved
5.71
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
c
l
o
n
e
f
u
d
g
e
h
u
m
p
h
n
y
m
p
h
v
i
x
e
n

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

meta

Failed

h
o
u
s
e
f
l
a
m
e
g
l
e
b
e
t
i
m
e
d
t
e
s
t
e
t
a
p
e
r

openai/gpt-4o

openai

Failed

c
r
a
n
e
l
o
o
s
e
d
e
p
t
h
e
x
a
l
t
r
e
s
e
t
e
v
i
c
t

anthropic/claude-3.7-sonnet

anthropic

6/6

c
r
a
n
e
s
l
i
d
e
t
o
q
u
e
t
h
e
m
e
t
w
e
a
k
t
w
e
e
t

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
d
e
l
v
e
e
m
b
e
r
p
e
n
n
e
b
e
v
e
l
f
e
w
e
r

x-ai/grok-3-mini-beta

x-ai

4/6

c
r
a
n
e
q
u
i
e
t
s
w
e
e
t
t
w
e
e
t

mistralai/mistral-medium-3

mistral

Failed

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

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