AI vs Puzzles

Back to Home
Puzzle#110

Countdown

Released: 2026-02-14


7
Models Tested
2
Solved
7
LLM Providers

Key:

Used
Unused

Score Threshold:

Within 7

google/gemini-2.0-flash-001

google

738Target
25
100
50
10
10
2

(100 * 10) - (50 + 10 + 2)

= 938

Failed

openai/gpt-4o

openai

738Target
25
100
50
10
10
2

((10 + 2) * 50) + 100 - 10

= 690

Failed

anthropic/claude-3.7-sonnet

anthropic

738Target
25
100
50
10
10
2

((100 - 2) * 10) - ((50 + 10) / 25)

= 977

Failed

mistralai/mistral-medium-3

mistral

738Target
25
100
50
10
10
2

(100 - (25 - 10)) * (50 - (10 / 2))

= 3825

Failed

deepseek/deepseek-chat-v3-0324

deepseek

738Target
25
100
50
10
10
2

(100 * (10 - 2)) + (50 - (25 - 10))

= 835

Failed

x-ai/grok-3-mini-beta

x-ai

738Target
25
100
50
10
10
2

((50 + 25) * 10) - (10 + 2)

= 738

Perfect Solution!

qwen/qwen3-235b-a22b

qwen

738Target
25
100
50
10
10
2

((100 + 25 - 2) * ((50 + 10) / 10))

= 738

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