AI vs Puzzles

Back to Home
Puzzle#1692

Wordle

Released: 2026-02-05

8
Models Tested
4
Solved
5.25
Avg. Attempts
8
LLM Providers
Correct
Present
Absent

openai/gpt-4o

openai

Failed

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

google/gemini-2.0-flash-001

google

2/6

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

deepseek/deepseek-chat-v3-0324

deepseek

2/6

c
r
a
n
e
s
p
o
r
t
s
l
o
o
p
s
w
o
o
p

mistralai/mistral-medium-3

mistral

Failed

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

anthropic/claude-3.7-sonnet

anthropic

Failed

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

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

meta

Failed

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

x-ai/grok-3-mini-beta

x-ai

2/6

c
r
a
n
e
g
h
o
s
t
s
l
o
o
p
s
w
o
o
p

qwen/qwen3-235b-a22b

qwen

2/6

c
r
a
n
e
s
l
u
m
p
s
t
o
o
p
s
w
o
o
p

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