AI vs Puzzles

Back to Home
Puzzle#1783

Wordle

Released: 2026-05-07

7
Models Tested
3
Solved
5.43
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

c
r
a
n
e
b
l
o
k
e
b
e
d
g
e
b
e
d
g
e
b
e
g
d
e
b
a
d
g
e

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

meta

Failed

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

mistralai/mistral-medium-3

mistral

Failed

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

openai/gpt-4o

openai

Failed

c
r
a
t
e
p
l
u
m
e
b
r
u
t
e
b
o
u
l
e
b
l
u
e
s
b
u
n
j
e

deepseek/deepseek-chat-v3-0324

deepseek

4/6

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

anthropic/claude-3.7-sonnet

anthropic

5/6

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

x-ai/grok-3-mini-beta

x-ai

5/6

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