AI vs Puzzles

Back to Home
Puzzle#1785

Wordle

Released: 2026-05-09

7
Models Tested
3
Solved
5.57
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

5/6

c
r
a
n
e
p
l
a
n
t
s
t
a
n
d
s
a
i
n
t
s
a
t
i
n

google/gemini-2.0-flash-001

google

6/6

c
r
a
n
e
p
a
i
n
s
b
a
i
n
s
s
a
i
n
t
s
n
a
i
t
s
a
t
i
n

openai/gpt-4o

openai

Failed

c
r
a
n
e
b
a
c
o
n
m
e
l
o
n
h
y
m
e
n
a
g
a
i
n
p
l
a
i
n

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

meta

Failed

h
o
u
s
e
s
t
a
m
p
s
l
a
n
t
s
t
a
n
t
s
a
n
t
a
s
a
n
s
y

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
p
l
a
n
k
a
d
o
r
n
t
a
n
g
y
m
a
n
i
a
b
a
n
j
o

x-ai/grok-3-mini-beta

x-ai

4/6

c
r
a
n
e
t
a
n
k
s
n
a
s
t
y
s
a
t
i
n

anthropic/claude-3.7-sonnet

anthropic

Failed

s
l
a
t
e
s
t
a
i
r
s
o
k
i
t
s
p
a
i
t
s
w
a
i
t
s
m
a
i
t

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