AI vs Puzzles

Back to Home
Puzzle#1764

Wordle

Released: 2026-04-18

7
Models Tested
2
Solved
6.00
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

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

openai/gpt-4o

openai

Failed

c
r
a
n
e
a
l
p
h
a
o
v
a
t
e
r
o
a
s
t
m
o
a
t
s
k
o
f
t
a

deepseek/deepseek-chat-v3-0324

deepseek

Failed

s
t
a
r
e
b
a
t
t
y
t
a
r
d
y
t
a
w
n
y
t
a
t
t
y
t
a
n
g
y

x-ai/grok-3-mini-beta

x-ai

6/6

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

mistralai/mistral-medium-3

mistral

Failed

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

anthropic/claude-3.7-sonnet

anthropic

Failed

r
a
i
s
e
p
a
t
c
h
w
a
l
t
y
m
a
t
t
y
b
a
t
t
y
g
a
u
t
y

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

meta

6/6

h
o
u
s
e
m
o
o
d
y
b
r
o
a
d
c
o
a
d
y
r
o
a
d
y
t
o
a
d
y

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