AI vs Puzzles

Back to Home
Puzzle#1740

Wordle

Released: 2026-03-25

7
Models Tested
3
Solved
5.86
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

6/6

c
r
a
n
e
r
o
b
e
y
f
i
b
e
r
l
i
t
e
r
s
i
z
e
r
w
i
s
e
r

openai/gpt-4o

openai

6/6

c
r
a
n
e
s
e
r
u
m
l
o
s
e
r
f
u
s
e
r
v
i
s
e
r
w
i
s
e
r

mistralai/mistral-medium-3

mistral

Failed

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

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

meta

Failed

h
o
u
s
e
f
e
n
c
e
s
t
e
e
p
s
p
a
c
e
s
l
i
c
e
g
l
o
b
e

anthropic/claude-3.7-sonnet

anthropic

Failed

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

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
p
r
e
e
n
m
e
r
r
y
p
e
r
k
y
r
e
b
e
l
r
e
n
e
w

x-ai/grok-3-mini-beta

x-ai

5/6

c
r
a
n
e
r
o
v
e
r
d
r
i
e
r
r
i
s
e
r
w
i
s
e
r

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