Released: 2026-05-28
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 8) - (10 + 8 + 6 + 9)
= 567
openai/gpt-4o
openai
(75 * 8) - (6 + 9)
= 585
mistralai/mistral-medium-3
mistral
((75 * (10 - (9 - 8))) * 8) + 6
= 5406
deepseek/deepseek-chat-v3-0324
deepseek
((75 + 10) * 6) + 8
= 518
minimax/minimax-m2.5
minimax
(75 + 8) * 6 + 10 + 9 + 8
= 525
moonshotai/kimi-k2.5
moonshot
75 * 8 - (9 - 6) * 10 + 8
= 578
z-ai/glm-5
z-ai
((75 - 9) * 8) + 10 + ((8 - 6))
= 540
anthropic/claude-sonnet-4.6
anthropic
75 * 8 - 10 + 8 * (9 - 6)
= 614
google/gemini-3-flash-preview
(75 + 8) * (8 - (10 - 9)) + 6
= 587
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.