AI vs Puzzles

Back to Home
Puzzle#1705

Wordle

Released: 2026-02-18

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

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
d
o
l
l
y
m
o
l
d
y
m
o
i
s
t
m
o
n
k
s
m
o
l
d
y

google/gemini-2.0-flash-001

google

Failed

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

openai/gpt-4o

openai

Failed

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

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

meta

Failed

h
o
u
s
e
b
o
u
r
g
f
o
u
g
h
c
o
u
g
h
m
o
u
g
h
m
o
u
t
h

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
s
o
u
t
h
l
o
u
s
y
c
o
u
l
d
b
u
l
k
y
g
l
u
o
n

x-ai/grok-3-mini-beta

x-ai

Failed

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

anthropic/claude-3.7-sonnet

anthropic

Failed

s
l
a
t
e
p
r
o
u
d
c
l
u
n
k
p
l
u
m
b
g
l
u
m
e
m
u
l
g
h

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