AI vs Puzzles

Back to Home
Puzzle#1766

Wordle

Released: 2026-04-20

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

openai/gpt-4o

openai

4/6

c
r
a
n
e
w
h
a
l
e
w
a
i
v
e
w
e
a
v
e

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
b
l
a
d
e
s
h
a
m
e
f
l
a
r
e
p
a
u
s
e
o
a
k
e
n

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
l
a
d
l
e
w
a
f
e
r
w
a
s
t
e
w
a
c
k
e
w
a
i
v
e

anthropic/claude-3.7-sonnet

anthropic

6/6

s
l
a
t
e
p
a
w
e
d
m
a
i
z
e
c
a
r
v
e
w
a
v
e
d
w
e
a
v
e

x-ai/grok-3-mini-beta

x-ai

Failed

c
r
a
n
e
b
l
a
m
e
s
h
a
k
e
a
g
a
t
e
e
v
a
d
e
v
a
l
u
e

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

meta

Failed

h
o
u
s
e
f
l
a
m
e
b
r
i
c
k
s
p
a
c
e
g
r
a
d
e
b
l
a
z
e

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
g
l
a
d
e
f
r
a
m
e
q
u
a
k
e
b
a
s
t
e
a
w
a
k
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