AI vs Puzzles

Back to Home
Puzzle#108

Countdown

Released: 2026-02-12


7
Models Tested
2
Solved
7
LLM Providers

Key:

Used
Unused

Score Threshold:

Within 7

mistralai/mistral-medium-3

mistral

873Target
75
7
6
8
7
9

((75 + 8) * (9 + 6)) - (7 / 7)

= 1244

Failed

openai/gpt-4o

openai

873Target
75
7
6
8
7
9

(75 * 9) + ((7 - 6) * 8)

= 683

Failed

deepseek/deepseek-chat-v3-0324

deepseek

873Target
75
7
6
8
7
9

((75 * (9 + 7)) - (8 + 7))

= 1185

Failed

anthropic/claude-3.7-sonnet

anthropic

873Target
75
7
6
8
7
9

75 * (9 + 6 - 7)

= 600

Failed

google/gemini-2.0-flash-001

google

873Target
75
7
6
8
7
9

((75 + 7) * 9) + (8 - 6)

= 740

Failed

qwen/qwen3-235b-a22b

qwen

873Target
75
7
6
8
7
9

9*(75 + 7 + 7 + 8)

= 873

Perfect Solution!

x-ai/grok-3-mini-beta

x-ai

873Target
75
7
6
8
7
9

9 * (75 + 7 + 7 + 8)

= 873

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