AI vs Puzzles

Back to Home
Puzzle#1706

Wordle

Released: 2026-02-19

7
Models Tested
4
Solved
5.43
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
u
n
i
o
n
b
l
o
c
k
w
i
r
e
s
o
s
i
e
r
s
o
i
l
s

mistralai/mistral-medium-3

mistral

Failed

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

openai/gpt-4o

openai

6/6

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

deepseek/deepseek-chat-v3-0324

deepseek

5/6

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

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

meta

Failed

h
o
u
s
e
h
o
v
e
r
h
o
l
d
s
h
o
s
t
s
h
o
t
l
y
h
o
r
t
s

x-ai/grok-3-mini-beta

x-ai

5/6

p
e
s
t
o
s
t
o
n
y
t
o
r
u
s
b
o
a
s
t
h
o
i
s
t

anthropic/claude-3.7-sonnet

anthropic

4/6

s
t
a
r
e
t
w
i
s
t
m
o
i
s
t
h
o
i
s
t

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