A Coding Guide to Google Research’s MSEB: Writing Sound Encoders to the Benchmark Contract and Scoring Them Across Classification, Clustering, Retrieval and Segmentation
15 min
The Alignment Illusion in Multimodal Large Language Models
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
StudentBench: AI and human tutoring yield equivalent GRE learning gains
GPT-6 Astra has gained the ability to drive a car
2 min
Introducing MentalHealthBench
8 min
Multi-View Fusion for Encrypted C2 Detection: A Leakage-Controlled Measurement Study of Evaluation Pitfalls
SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It
Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen
The Delegation Blind Spot: Auditing Product Decisions from Agent Choices
Rethinking Backdoor Repair Evaluation: Distinguishing Aggregate Clean Utility from Benign Performance Preservation
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
SSP-Bench: A Hybrid Data Generation Framework for Safety, Security, and Privacy Evaluation
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
DolphinBench: Mapping the Pareto Frontier of Agent Memory
Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences
OSWorld-Pro: Process-based Evaluation for Computer Use Agents
The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora
Bristol researchers say medicine already knows how to handle black boxes and AI could learn from it
2 min
Google Gemini Broke Into Real Company Systems After Security Test Domain Mix-Up
2 min1
QuranicMMLU: A Cognitively-Aware Benchmark for Evaluating Generative AI Solutions on Quranic Linguistic Knowledge
1