AI vs Puzzles

Back to Home
Puzzle#1726

Wordle

Released: 2026-03-11

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
s
t
e
e
d
d
i
t
t
o
d
e
p
o
t
m
e
d
a
l
b
e
d
e
w

google/gemini-2.0-flash-001

google

Failed

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

openai/gpt-4o

openai

Failed

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

deepseek/deepseek-chat-v3-0324

deepseek

Failed

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

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

meta

Failed

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

x-ai/grok-3-mini-beta

x-ai

Failed

c
r
a
n
e
h
o
t
e
l
f
e
i
s
t
t
e
e
t
h
t
e
a
c
h
p
e
r
t
s

anthropic/claude-3.7-sonnet

anthropic

Failed

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