Released: 2026-03-01
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 75) * 4 + 50 + 25 - 2
= 773
openai/gpt-4o
openai
(100 + 75 + 50) * 4 - 2
= 898
mistralai/mistral-medium-3
mistral
(100 * 75) - (50 * 25) - (4 * 2)
= 6242
google/gemini-3-flash-preview
(75 * (100 - 50) / 25) - 2 + 4
= 152
anthropic/claude-3.7-sonnet
anthropic
75 * 100 / 25 * 2 + 50 - 4
= 646
google/gemini-2.0-flash-001
(75 + 100) * 4 - 25 + 50 - 2
= 723
minimax/minimax-m2.5
minimax
100 * (4 + 2) + 75
= 675
x-ai/grok-3-mini-beta
x-ai
100 * (4 + 2) + 75
= 675
moonshotai/kimi-k2.5
moonshot
(100 + 4) * (75 / 25 * 2) + 50
= 674
anthropic/claude-sonnet-4.6
anthropic
75 * (4 + 100 / 50) + 25 - 2
= 473
z-ai/glm-5
z-ai
(100 + 75) * 4 - 25 - 2
= 673
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.