AI vs Puzzles

Back to Home
Puzzle#1700

Wordle

Released: 2026-02-13

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

mistralai/mistral-medium-3

mistral

Failed

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

google/gemini-2.0-flash-001

google

Failed

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

openai/gpt-4o

openai

2/6

c
r
a
n
e
c
l
i
m
b
c
o
m
e
t
m
o
c
h
a
m
o
u
c
h
m
o
o
c
h

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

meta

Failed

h
o
u
s
e
h
o
a
r
d
c
o
h
o
l
c
h
o
i
r
u
c
h
o
s
y
h
o
c
h

anthropic/claude-3.7-sonnet

anthropic

Failed

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

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
c
l
o
u
d
c
o
m
e
t
c
r
i
m
p
c
o
m
m
a
c
o
v
e
y

x-ai/grok-3-mini-beta

x-ai

2/6

c
r
a
n
e
c
l
u
m
p
m
o
c
h
i
m
o
o
c
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