AI vs Puzzles

Back to Home
Puzzle#200

Countdown

Released: 2026-05-15


10
Models Tested
0
Solved
9
LLM Providers

Key:

Used
Unused

Score Threshold:

Within 7

google/gemini-3-flash-preview

google

682Target
25
100
50
10
1
5

((100 + 10 + 25 + 1) * 5) - 50

= 630

Failed

MoonshotAI

moonshotai/kimi-k2.5

moonshot

682Target
25
100
50
10
1
5

(25 * 5) + (100 - 50) - 1 + 10

= 184

Failed

Minimax

minimax/minimax-m2.5

minimax

682Target
25
100
50
10
1
5

50 * (10 + 1) + 100 + 25 + 5

= 680

Close; 2 away

x-ai/grok-3-mini-beta

x-ai

682Target
25
100
50
10
1
5

100 * (5 + 1) + 50 + 25 + 10

= 685

Close; 3 away

google/gemini-2.0-flash-001

google

682Target
25
100
50
10
1
5

(50 * 10) + 100 + 25 + 5 + 1

= 631

Failed

Z.ai

z-ai/glm-5

z-ai

682Target
25
100
50
10
1
5

((25 - 1) * 5 * 10) - (100 + 50)

= 1050

Failed

openai/gpt-4o

openai

682Target
25
100
50
10
1
5

((100 + 50) * 5) + (25 + 10 - 1)

= 784

Failed

deepseek/deepseek-chat-v3-0324

deepseek

682Target
25
100
50
10
1
5

(100 - (50 - (25 - 10) - 1)) * 5

= 330

Failed

mistralai/mistral-medium-3

mistral

682Target
25
100
50
10
1
5

((100 + 50) * (5 + 1)) + (25 - 10)

= 915

Failed

anthropic/claude-sonnet-4.6

anthropic

682Target
25
100
50
10
1
5

100 * (5 + 1) + 50 * (25 - 10)

= 1350

Failed

Methodology Note

Each model receives the same prompt with the numbers to use. Models are tasked with creating an expression using only arithmetic operations to reach the target number. Each number can only be used once and you do not have to use all the numbers. Their answers are evaluated without feedback or retries.

Leaderboard