AI vs Puzzles

Back to Home
Puzzle#1715

Wordle

Released: 2026-02-28

7
Models Tested
2
Solved
5.57
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
b
r
o
a
d
h
a
r
l
d
r
a
d
a
r
w
o
r
d
s
p
u
r
r
d

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
g
r
a
i
l
b
a
r
k
a
d
r
a
m
a
r
a
d
a
r
a
r
d
o
r

anthropic/claude-3.7-sonnet

anthropic

5/6

s
l
a
t
e
c
h
a
r
m
p
h
a
r
x
d
i
a
r
y
h
y
d
r
a

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

meta

Failed

h
o
u
s
e
h
a
t
c
h
h
a
u
n
t
h
a
n
d
s
h
a
r
d
y
h
a
y
r
d

x-ai/grok-3-mini-beta

x-ai

4/6

c
r
a
n
e
p
a
i
r
s
h
e
a
r
d
h
y
d
r
a

mistralai/mistral-medium-3

mistral

Failed

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

openai/gpt-4o

openai

Failed

f
l
i
n
g
c
o
a
c
h
s
h
a
k
y
h
a
i
r
y
h
a
r
p
y
h
a
r
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