AI vs Puzzles

Back to Home
Puzzle#1765

Wordle

Released: 2026-04-19

7
Models Tested
3
Solved
5.14
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

Failed

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

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
c
l
a
n
g
w
a
n
d
a
m
a
m
b
a
p
a
n
t
a
d
o
n
n
a

anthropic/claude-3.7-sonnet

anthropic

3/6

s
l
a
t
e
s
h
a
r
d
s
t
a
n
d

openai/gpt-4o

openai

Failed

c
r
a
t
e
s
t
a
m
p
s
t
a
r
k
s
t
a
v
e
s
t
a
s
h
s
t
a
f
f

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

meta

Failed

h
o
u
s
e
b
l
a
s
t
c
a
s
t
s
t
a
l
e
s
s
t
a
r
k
s
t
a
t
s

x-ai/grok-3-mini-beta

x-ai

5/6

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

deepseek/deepseek-chat-v3-0324

deepseek

4/6

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

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