AI vs Puzzles

Back to Home
Puzzle#1757

Wordle

Released: 2026-04-11


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

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
t
r
u
e
r
b
l
u
e
s
p
o
w
e
r
p
u
r
e
r
p
i
q
u
e

anthropic/claude-3.7-sonnet

anthropic

3/6

c
r
a
t
e
b
r
i
d
e
p
r
u
d
e

openai/gpt-4o

openai

Failed

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

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
p
r
o
w
l
p
r
i
d
e
p
r
e
e
d
p
r
e
y
s
p
r
e
e
n

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

meta

Failed

h
o
u
s
e
b
r
u
z
e
t
r
u
c
e
p
r
u
n
e
p
u
l
s
e
p
u
r
g
e

deepseek/deepseek-chat-v3-0324

deepseek

4/6

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

x-ai/grok-3-mini-beta

x-ai

5/6

c
r
a
n
e
b
r
i
d
e
e
r
o
d
e
t
r
u
c
e
p
r
u
d
e

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