AI vs Puzzles

Back to Home
Puzzle#113

Countdown

Released: 2026-02-17


9
Models Tested
4
Solved
9
LLM Providers

Key:

Used
Unused

Score Threshold:

Within 7

openai/gpt-4o

openai

704Target
100
50
8
6
4
7

(8 * (100 - (7 - 6)))

= 792

Failed

deepseek/deepseek-chat-v3-0324

deepseek

704Target
100
50
8
6
4
7

(100 + 6) * (7 - (8 / (50 / 4)))

= 674

Failed

anthropic/claude-3.7-sonnet

anthropic

704Target
100
50
8
6
4
7

(100 * 7) + (4 * 6)

= 724

Failed

mistralai/mistral-medium-3

mistral

704Target
100
50
8
6
4
7

((100 + 50) * (8 - (7 - 6))) + 4

= 1054

Failed

google/gemini-2.0-flash-001

google

704Target
100
50
8
6
4
7

(100 * 7) + 6 - (8 - 4) + 50

= 752

Failed

Minimax

minimax/minimax-m2.5

minimax

704Target
100
50
8
6
4
7

100 * 7 + 4

= 704

Perfect Solution!

Z.ai

z-ai/glm-5

z-ai

704Target
100
50
8
6
4
7

(100 * 7) + 4

= 704

Perfect Solution!

x-ai/grok-3-mini-beta

x-ai

704Target
100
50
8
6
4
7

(100 * 7) + 4

= 704

Perfect Solution!

MoonshotAI

moonshotai/kimi-k2.5

moonshot

704Target
100
50
8
6
4
7

7 * 100 + 4

= 704

Perfect Solution!

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