AI vs Puzzles

Back to Home
Puzzle#1784

Wordle

Released: 2026-05-08

7
Models Tested
2
Solved
5.86
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
r
a
t
i
o
d
r
a
i
s
p
a
r
k
a
m
a
r
c
a
r
a
m
a
n

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

meta

Failed

h
o
u
s
e
v
a
u
l
t
g
i
v
e
n
m
a
u
n
d
m
a
r
c
h
m
u
r
k
y

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
b
r
o
a
d
b
l
a
s
t
h
a
b
i
t
r
a
b
b
i
a
r
b
o
r

openai/gpt-4o

openai

6/6

c
r
a
n
e
a
l
a
r
m
s
m
a
r
t
a
m
b
e
r
u
m
b
a
r
u
m
b
r
a

anthropic/claude-3.7-sonnet

anthropic

Failed

c
r
a
n
e
p
a
s
t
a
d
r
a
m
a
k
a
r
m
a
l
a
r
v
a
a
r
o
m
a

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
r
a
t
i
o
a
r
o
m
a
a
r
m
a
d
r
a
m
a
l
m
a
r
s
h

x-ai/grok-3-mini-beta

x-ai

5/6

c
r
a
n
e
r
a
p
i
d
h
u
m
o
r
a
w
f
u
l
u
m
b
r
a

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