AI vs Puzzles

Back to Home
Puzzle#1768

Wordle

Released: 2026-04-22

7
Models Tested
1
Solved
5.57
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
l
o
r
e
s
w
o
r
s
e
h
o
r
s
e
c
o
r
s
e
b
o
r
e
r

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

meta

Failed

h
o
u
s
e
g
l
o
v
e
m
o
o
s
e
b
o
r
e
s
r
o
b
e
s
s
c
o
r
e

openai/gpt-4o

openai

Failed

s
l
a
t
e
s
h
o
r
e
s
p
o
r
e
s
c
o
r
e
s
w
o
r
e
s
t
o
r
e

anthropic/claude-3.7-sonnet

anthropic

Failed

s
l
a
t
e
s
h
i
n
e
s
p
o
n
e
s
t
o
n
e
s
c
o
n
e
s
w
o
n
e

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
p
r
o
n
e
g
r
o
i
n
b
r
o
w
n
m
i
c
r
o
h
o
r
d
e

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
r
e
n
e
w
n
e
r
d
y
i
n
f
e
r
g
e
n
r
e
n
e
r
v
e

x-ai/grok-3-mini-beta

x-ai

3/6

c
r
a
n
e
n
o
r
s
e
s
n
o
r
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