AI vs Puzzles

Back to Home
Puzzle#1775

Wordle

Released: 2026-04-29

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

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
b
r
o
a
d
g
r
a
v
y
a
r
o
m
a
f
l
o
r
a
s
a
l
a
d

mistralai/mistral-medium-3

mistral

Failed

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

openai/gpt-4o

openai

Failed

c
r
a
n
e
a
r
m
o
r
l
a
r
k
s
b
r
a
l
y
u
l
t
r
a
l
a
r
u
m

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

meta

Failed

h
o
u
s
e
t
r
u
t
h
b
r
u
n
t
c
r
u
s
h
c
u
r
l
y
u
l
t
r
a

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
d
r
a
m
a
a
r
r
a
y
t
e
r
r
a
p
a
r
a
s
b
a
r
b
a

x-ai/grok-3-mini-beta

x-ai

5/6

c
r
a
n
e
p
a
r
t
y
v
i
r
a
l
m
o
r
a
l
r
u
r
a
l

anthropic/claude-3.7-sonnet

anthropic

6/6

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

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