AI vs Puzzles

Back to Home
Puzzle#1725

Wordle

Released: 2026-03-10

7
Models Tested
2
Solved
5.71
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

Failed

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

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
b
l
a
s
t
s
a
l
a
d
s
l
a
s
h
l
a
s
a
h
a
s
h
l
y

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

meta

Failed

h
o
u
s
e
s
h
o
t
s
s
h
o
c
k
s
h
o
p
s
s
h
o
r
t
s
h
o
c
k

openai/gpt-4o

openai

Failed

c
r
a
n
e
l
a
u
g
h
c
h
a
l
k
h
a
l
a
l
s
h
a
w
l
s
h
a
l
l

anthropic/claude-3.7-sonnet

anthropic

6/6

s
t
a
r
e
s
a
u
n
a
s
l
a
s
h
s
h
a
l
e
s
h
a
l
l
s
h
o
a
l

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
l
a
s
e
r
s
l
a
t
e
s
a
l
a
d
s
a
l
s
a
s
a
l
s
a

x-ai/grok-3-mini-beta

x-ai

4/6

c
r
a
n
e
q
u
a
i
l
t
o
t
a
l
s
h
o
a
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