AI vs Puzzles

Back to Home
Puzzle#1759

Wordle

Released: 2026-04-13

7
Models Tested
3
Solved
5.43
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

openai/gpt-4o

openai

4/6

c
r
a
n
e
w
e
n
c
h
f
i
n
e
s
e
l
f
i
n

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
l
i
o
n
s
f
l
i
n
t
i
n
l
a
y
n
i
f
t
y
l
i
n
e
r

mistralai/mistral-medium-3

mistral

Failed

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

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

meta

Failed

h
o
u
s
e
f
l
a
k
e
f
e
l
d
s
l
f
a
m
e
g
l
e
b
e
f
l
u
t
e

anthropic/claude-3.7-sonnet

anthropic

Failed

c
r
a
n
e
p
o
i
n
t
f
i
e
n
d
k
n
i
f
e
h
i
n
g
e
l
i
n
e
f

deepseek/deepseek-chat-v3-0324

deepseek

6/6

c
r
a
n
e
l
i
n
e
s
a
l
i
e
n
o
l
i
v
e
e
l
k
i
n
e
l
f
i
n

x-ai/grok-3-mini-beta

x-ai

4/6

c
r
a
n
e
d
e
n
i
m
s
t
e
i
n
e
l
f
i
n

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