انسَ الذكاء العام الاصطناعي—أفضل نماذج الذكاء الاصطناعي لا تزال تواجه صعوبة في الرياضيات

Forget AGI—Top AI Models Still Struggle With Math

Forget AGI—Top AI Models Still Struggle With Math Price data byDecryptNewsArtificial IntelligenceForget AGI—Top AI Models Still Struggle With MathNew benchmark study results show leading AI models still lag humans in visual math reasoning.By Jason NelsonEdited by Sebastian SinclairMar 18, 2026Mar 18, 20264 min readSource: DecryptCreate an account to save your articles.Add on GoogleAdd Decrypt as your preferred source to see more of our stories on Google.In brief MATHVISTA, built with more than 6,000 annotated datapoints from Sahara AI, tests AI models on multimodal math reasoning. GPT-4V scored 49.9%, the highest result among 12 models tested, but still 10.4 percentage points below human performance. Researchers say progress toward AGI may depend less on model size than on better training and evaluation data. Artificial general intelligence, or AGI, is often described as a system that ca

Source: https://decrypt.co/361474/forget-agi-top-ai-models-still-struggle-with-math