AI vs Puzzles

Back to Home
Puzzle#1713

Wordle

Released: 2026-02-26

7
Models Tested
5
Solved
4.71
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

openai/gpt-4o

openai

3/6

c
r
y
p
t
c
l
o
w
n
l
a
n
c
e

mistralai/mistral-medium-3

mistral

Failed

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

anthropic/claude-3.7-sonnet

anthropic

4/6

s
l
a
n
e
c
a
l
n
e
d
a
n
c
e
l
a
n
c
e

google/gemini-2.0-flash-001

google

6/6

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

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

meta

Failed

h
o
u
s
e
g
l
o
b
e
f
l
a
m
e
b
l
a
z
e
l
a
n
e
s
l
a
n
s
e

deepseek/deepseek-chat-v3-0324

deepseek

5/6

c
r
a
n
e
c
a
n
e
d
a
c
n
e
d
f
a
n
c
y
l
a
n
c
e

x-ai/grok-3-mini-beta

x-ai

3/6

c
r
a
n
e
d
a
n
c
e
l
a
n
c
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