AI vs Puzzles

Back to Home
Puzzle#1782

Wordle

Released: 2026-05-06

7
Models Tested
3
Solved
5.43
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

openai/gpt-4o

openai

4/6

c
r
a
n
e
l
i
n
e
n
l
i
n
e
n
l
i
k
e
n

mistralai/mistral-medium-3

mistral

Failed

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

google/gemini-2.0-flash-001

google

Failed

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

deepseek/deepseek-chat-v3-0324

deepseek

5/6

c
r
a
n
e
l
i
n
e
d
l
i
t
h
e
l
i
b
e
l
l
i
k
e
n

x-ai/grok-3-mini-beta

x-ai

5/6

c
r
a
n
e
i
n
l
e
t
l
i
m
e
n
l
i
v
e
n
l
i
k
e
n

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

meta

Failed

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

anthropic/claude-3.7-sonnet

anthropic

Failed

s
l
a
t
e
p
r
i
d
e
w
h
i
l
e
b
l
i
n
k
f
i
n
c
k
k
i
n
e
l

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