Skip to content
AI.info
News
Tools
Research
Learn
AI.info
Dhruv Kumar
Explore Dhruv Kumar on AI.info.
Beyond Accuracy: Diagnosing Algebraic Reasoning Failures in LLMs Across Nine Complexity Dimensions
The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation
CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics
Page 1