AI vs Puzzles

Back to Home
Puzzle#1712

Wordle

Released: 2026-02-25

7
Models Tested
3
Solved
5.29
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

openai/gpt-4o

openai

5/6

c
r
a
n
e
s
o
w
e
r
s
e
r
i
f
s
h
r
e
w
s
h
r
e
d

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

meta

4/6

h
o
u
s
e
s
h
e
a
r
s
h
a
r
e
s
h
r
e
d

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
p
r
o
w
l
d
r
i
e
r
r
e
d
e
s
s
e
d
e
r
s
e
d
a
n

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
l
o
r
e
s
c
r
u
e
s
d
r
e
s
s
w
e
r
r
e
g
r
i
m
e

anthropic/claude-3.7-sonnet

anthropic

Failed

s
l
a
t
e
s
p
o
r
e
s
h
e
r
e
s
h
i
e
r
s
h
e
r
d
s
i
r
e
d

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
t
r
i
e
d
b
o
r
e
d
f
i
r
e
d
g
r
e
e
d
m
e
r
e
d

x-ai/grok-3-mini-beta

x-ai

4/6

s
l
a
t
e
s
e
r
u
m
s
h
r
e
w
s
h
r
e
d

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