AI vs Puzzles

Back to Home
Puzzle#1716

Wordle

Released: 2026-03-01

7
Models Tested
3
Solved
5.29
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
m
o
o
s
e
b
i
k
e
e
d
u
k
e
s
l
u
c
k
y
p
l
u
n
k

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
c
l
o
v
e
b
l
a
d
e
f
l
y
l
e
f
l
o
r
e
f
l
u
t
e

openai/gpt-4o

openai

5/6

c
r
a
n
e
s
p
i
k
e
b
l
o
k
e
f
l
a
k
e
f
l
u
k
e

anthropic/claude-3.7-sonnet

anthropic

4/6

s
l
a
t
e
w
h
i
l
e
p
l
u
m
e
f
l
u
k
e

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

meta

Failed

h
o
u
s
e
t
r
u
c
e
f
l
u
m
e
f
l
u
t
e
f
l
a
m
e
f
l
u
t
e

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
d
e
l
v
e
b
e
z
e
l
h
e
l
l
o
e
l
b
o
w
l
a
b
e
l

x-ai/grok-3-mini-beta

x-ai

4/6

a
r
o
s
e
f
l
u
t
e
f
l
u
m
e
f
l
u
k
e

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