AI vs Puzzles

Back to Home
Puzzle#1770

Wordle

Released: 2026-04-24

7
Models Tested
4
Solved
4.57
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

4/6

c
r
a
n
e
b
r
i
n
k
p
r
o
w
l
d
r
u
n
k

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
i
r
o
n
s
u
r
b
a
n
r
u
n
t
s
n
u
r
s
e
u
r
n
a
l

openai/gpt-4o

openai

Failed

c
r
a
t
e
w
r
i
n
g
b
u
r
n
t
r
u
n
n
y
n
u
r
s
e
u
n
o
r
n

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

meta

Failed

h
o
u
s
e
b
r
u
n
t
c
r
u
n
k
g
r
u
n
t
t
r
u
n
k
p
r
a
n
k

deepseek/deepseek-chat-v3-0324

deepseek

4/6

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

x-ai/grok-3-mini-beta

x-ai

3/6

c
r
a
n
e
g
r
i
n
d
d
r
u
n
k

anthropic/claude-3.7-sonnet

anthropic

3/6

c
r
a
n
e
p
r
i
n
t
d
r
u
n
k

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