AI vs Puzzles

Back to Home
Puzzle#1744

Wordle

Released: 2026-03-29

7
Models Tested
6
Solved
4.00
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

4/6

c
r
a
n
e
c
o
u
c
h
c
u
s
h
y
c
h
u
m
p

openai/gpt-4o

openai

4/6

c
r
a
n
e
c
o
u
c
h
c
h
u
r
l
c
h
u
m
p

anthropic/claude-3.7-sonnet

anthropic

4/6

s
t
o
r
e
b
a
l
m
y
c
h
i
m
p
c
h
u
m
p

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

meta

3/6

h
o
u
s
e
t
h
u
m
p
c
h
u
m
p

deepseek/deepseek-chat-v3-0324

deepseek

Failed

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

x-ai/grok-3-mini-beta

x-ai

4/6

c
r
a
n
e
c
l
o
c
k
c
h
i
p
s
c
h
u
m
p

google/gemini-2.0-flash-001

google

3/6

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

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