AI vs Puzzles

Back to Home
Puzzle#1694

Wordle

Released: 2026-02-07

8
Models Tested
8
Solved
4.75
Avg. Attempts
8
LLM Providers
Correct
Present
Absent

openai/gpt-4o

openai

2/6

t
a
b
l
e
b
l
e
a
t

google/gemini-2.0-flash-001

google

2/6

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

anthropic/claude-3.7-sonnet

anthropic

2/6

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

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

meta

2/6

h
o
u
s
e
f
l
a
m
e
b
l
a
d
e
b
l
a
z
e
b
l
a
s
t
b
l
e
a
t

deepseek/deepseek-chat-v3-0324

deepseek

2/6

c
r
a
n
e
p
l
a
n
e
b
l
a
m
e
b
l
e
a
k
b
l
e
a
t

mistralai/mistral-medium-3

mistral

2/6

c
r
a
n
e
l
a
m
a
s
d
a
u
n
t
b
l
a
t
e
b
l
e
n
t
b
l
e
a
t

x-ai/grok-3-mini-beta

x-ai

2/6

c
r
a
n
e
e
q
u
a
l
d
e
l
a
y
g
l
e
a
m
p
l
e
a
s
b
l
e
a
t

qwen/qwen3-235b-a22b

qwen

2/6

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

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