AI vs Puzzles

Back to Home
Puzzle#111

Countdown

Released: 2026-02-15


9
Models Tested
4
Solved
9
LLM Providers

Key:

Used
Unused

Score Threshold:

Within 7

google/gemini-2.0-flash-001

google

553Target
75
7
7
7
1
10

(75 * 7) + (10 - 1) - 7

= 527

Failed

mistralai/mistral-medium-3

mistral

553Target
75
7
7
7
1
10

((75 * 7) * (7 + 1)) + (10 * 7)

= 4270

Failed

openai/gpt-4o

openai

553Target
75
7
7
7
1
10

(75 * 7) + (7 * 10) + 1

= 596

Failed

deepseek/deepseek-chat-v3-0324

deepseek

553Target
75
7
7
7
1
10

(75 - (7 / 7)) * (10 - 1)

= 666

Failed

x-ai/grok-3-mini-beta

x-ai

553Target
75
7
7
7
1
10

((75 + (10 - 7 + 1)) * 7)

= 553

Perfect Solution!

Z.ai

z-ai/glm-5

z-ai

553Target
75
7
7
7
1
10

7 * (75 + 7 + 7 - 10)

= 553

Perfect Solution!

MoonshotAI

moonshotai/kimi-k2.5

moonshot

553Target
75
7
7
7
1
10

(75 + 10) * 7 - (7 - 1) * 7

= 553

Perfect Solution!

anthropic/claude-3.7-sonnet

anthropic

553Target
75
7
7
7
1
10

75 * 7 + 7 * 7 - 1

= 573

Failed

qwen/qwen3-235b-a22b

qwen

553Target
75
7
7
7
1
10

(75 * 7) + (7 * (10 + 1 - 7))

= 553

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