AI vs Puzzles

Back to Home
Puzzle#1787

Wordle

Released: 2026-05-11

6
Models Tested
1
Solved
5.67
Avg. Attempts
6
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
d
u
n
n
o
p
e
n
e
s
m
e
l
e
e
d
e
m
o
n
l
e
p
e
r

google/gemini-2.0-flash-001

google

Failed

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

openai/gpt-4o

openai

Failed

c
r
a
n
e
s
t
o
n
e
l
i
n
e
d
a
n
g
e
l
c
l
o
n
e
k
n
e
l
l

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
t
e
p
e
o
n
y
d
e
n
l
y
v
e
n
l
y
p
e
n
n
y
g
e
n
n
y

x-ai/grok-3-mini-beta

x-ai

4/6

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

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

meta

Failed

h
o
u
s
e
g
l
o
b
e
f
l
a
m
e
g
l
e
b
e
k
n
i
f
e
f
l
u
t
e

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