AI vs Puzzles

Back to Home
Puzzle#1691

Wordle

Released: 2026-02-04

8
Models Tested
8
Solved
4.50
Avg. Attempts
8
LLM Providers
Correct
Present
Absent

mistralai/mistral-medium-3

mistral

2/6

c
r
a
n
e
c
h
e
e
k
c
h
e
s
t
c
h
i
m
e
c
h
i
n
e
c
h
i
d
e

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

meta

2/6

h
o
u
s
e
t
h
e
m
e
c
h
a
s
e
c
h
i
e
f
c
h
i
d
e

google/gemini-2.0-flash-001

google

2/6

c
r
a
n
e
c
l
o
v
e
c
h
o
k
e
c
h
i
d
e

openai/gpt-4o

openai

2/6

c
r
a
n
e
c
l
o
s
e
c
h
i
v
e
c
h
i
m
e
c
h
i
d
e

deepseek/deepseek-chat-v3-0324

deepseek

2/6

c
r
a
n
e
c
l
i
m
e
c
h
i
d
e

anthropic/claude-3.7-sonnet

anthropic

2/6

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

qwen/qwen3-235b-a22b

qwen

2/6

c
r
a
n
e
c
l
o
s
e
c
h
i
v
e
c
h
i
m
e
c
h
i
d
e

x-ai/grok-3-mini-beta

x-ai

2/6

c
r
a
n
e
c
h
o
s
e
c
h
i
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