AI vs Puzzles

Back to Home
Puzzle#235

Countdown

Released: 2026-06-19


8
Models Tested
2
Solved
8
LLM Providers

Key:

Used
Unused

Score Threshold:

Within 7

mistralai/mistral-medium-3

mistral

329Target
75
25
50
100
6
7

((75 + 100) * (7 - (6 - (25 / 50))))

= 262

Failed

openai/gpt-4o

openai

329Target
75
25
50
100
6
7

(6 * 50) + 75 - (100 / 25)

= 371

Failed

Z.ai

z-ai/glm-5

z-ai

329Target
75
25
50
100
6
7

(75 * 50) / 25 + 100 + 7 + 6

= 263

Failed

deepseek/deepseek-chat-v3-0324

deepseek

329Target
75
25
50
100
6
7

(75 * (6 - (100 / (50 + 25)))) + 7

= 357

Failed

Minimax

minimax/minimax-m2.5

minimax

329Target
75
25
50
100
6
7

(75-50)*(6+7)+(100/25)

= 329

Perfect Solution!

MoonshotAI

moonshotai/kimi-k2.5

moonshot

329Target
75
25
50
100
6
7

7 * (100 - 50 - 6 + 75 / 25)

= 329

Perfect Solution!

anthropic/claude-sonnet-4.6

anthropic

329Target
75
25
50
100
6
7

75 * 6 - 100 + 25 + 50 / 7

= 382

Failed

google/gemini-3-flash-preview

google

329Target
75
25
50
100
6
7

(75 * 7) - (100 + 50 + 25 + 6)

= 344

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