🧠 AI⚪ Neutral

Classroom Final Exam: An Instructor-Tested Reasoning Benchmark

arXiv – CS AI|Chongyang Gao, Diji Yang, Shuyan Zhou, Xichen Yan, Luchuan Song, Shuo Li, Kezhen Chen|March 4, 2026 at 05:00 AM|1 views

🤖AI Summary

Researchers introduce CFE-Bench, a new multimodal benchmark for evaluating AI reasoning across 20+ STEM domains using authentic university exam problems. The best performing model, Gemini-3.1-pro-preview, achieved only 59.69% accuracy, highlighting significant gaps in AI reasoning capabilities, particularly in maintaining correct intermediate states through multi-step solutions.

Key Takeaways

→CFE-Bench uses real university homework and exam problems with instructor solutions to test AI reasoning across STEM fields.
→Top AI model Gemini-3.1-pro-preview scored only 59.69% accuracy, showing substantial room for improvement.
→AI models struggle to maintain correct intermediate states throughout complex multi-step problem solving.
→Current models use more reasoning steps than human instructors, indicating lower efficiency and higher error risk.
→The benchmark reveals frontier AI models can answer sub-questions correctly but fail at comprehensive reasoning flows.

#ai-benchmarking #llm-evaluation #reasoning-capabilities #stem-education #gemini #multimodal-ai #academic-testing #ai-limitations

Read Original →via arXiv – CS AI

Act on this with AI

Stay ahead of the market.

Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.

Connect Wallet to AI →How it works

AI1h ago

Warren Buffett complained for decades that boosting profits by excluding exec stock comp was ‘cynical’—Nvidia just surprised Wall Street and agreed

Nvidia surprised Wall Street by agreeing to include executive stock compensation in its profit calculations, addressing a decades-old complaint by Warren Buffett about excluding such costs. This accounting change will likely boost Nvidia's credibility with investors while potentially pressuring competitors to follow suit.

AI4h ago

A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities

Researchers introduced NeuroCognition, a new benchmark for evaluating LLMs based on neuropsychological tests, revealing that while models show unified capability across tasks, they struggle with foundational cognitive abilities. The study found LLMs perform well on text but degrade with images and complexity, suggesting current models lack core adaptive cognition compared to human intelligence.

AI4h ago

Estimating Visual Attribute Effects in Advertising from Observational Data: A Deepfake-Informed Double Machine Learning Approach

Researchers developed DICE-DML, a new framework that uses deepfake technology and machine learning to measure causal effects of visual attributes in digital advertising. The method addresses bias issues in standard approaches when analyzing how image elements like skin tone affect consumer engagement on social media platforms.