Released: 2026-02-13
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(100 * 7) + (7 * 7) - (3 * 2)
= 743
openai/gpt-4o
openai
(100 * 7) + (7 * (3 + 2))
= 735
anthropic/claude-3.7-sonnet
anthropic
(100 * 7) + (7 - 2) * 3
= 715
deepseek/deepseek-chat-v3-0324
deepseek
(100 * 7) + (7 * 7) - (3 + 2)
= 744
x-ai/grok-3-mini-beta
x-ai
((100 * 7) + (7 * 7 - 3))
= 746
google/gemini-2.0-flash-001
(100 * 7) + 7 + 7 * 2 + 3
= 724
qwen/qwen3-235b-a22b
qwen
100*7 + 7*7 - 3
= 746
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.