AI vs Puzzles

Back to Home
Puzzle#1737

Wordle

Released: 2026-03-22

7
Models Tested
5
Solved
5.14
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

3/6

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

openai/gpt-4o

openai

Failed

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

deepseek/deepseek-chat-v3-0324

deepseek

4/6

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

x-ai/grok-3-mini-beta

x-ai

6/6

c
r
a
n
e
a
l
o
f
t
i
d
y
l
l
s
p
i
l
l
q
u
a
i
l
b
a
s
i
l

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
l
a
t
h
e
b
l
a
m
e
b
a
l
m
y
b
l
a
z
e
b
l
a
n
d

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

meta

6/6

h
o
u
s
e
b
l
a
s
t
b
l
u
r
s
b
a
n
k
s
b
a
s
a
l
b
a
s
i
l

anthropic/claude-3.7-sonnet

anthropic

5/6

c
r
a
n
e
p
o
s
a
t
b
i
s
a
m
b
i
s
h
a
b
a
s
i
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