AI vs Puzzles

Back to Home
Puzzle#1761

Wordle

Released: 2026-04-15

7
Models Tested
2
Solved
5.57
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
d
u
n
n
o
l
u
n
c
h
u
n
i
t
y
m
o
u
n
d
u
n
d
u
e

google/gemini-2.0-flash-001

google

Failed

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

openai/gpt-4o

openai

Failed

c
r
a
n
e
s
n
e
e
r
m
i
n
c
e
l
u
n
e
n
u
n
d
e
r
q
u
e
e
n

anthropic/claude-3.7-sonnet

anthropic

4/6

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

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

meta

Failed

h
o
u
s
e
u
n
i
t
e
l
u
n
g
e
b
u
n
g
y
b
u
n
g
e
b
u
n
g
e

x-ai/grok-3-mini-beta

x-ai

5/6

c
r
a
n
e
l
e
m
o
n
s
e
v
e
n
f
e
i
g
n
b
e
g
u
n

deepseek/deepseek-chat-v3-0324

deepseek

Failed

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

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