A new AI benchmark tests whether chatbots protect human well-being

Most AI benchmarks measure intelligence and instruction-following rather than psychological safety. Humane Bench evaluates ...
The National Law Review

HackerRank Introduces New Benchmark to Assess Advanced AI Models

Industry Leader Known for Software Development Skills Expertise Introduces Real-World Benchmark of AI Software Development Capabilities CUPERTINO, Calif., Feb. 11, 2025 (GLOBE NEWSWIRE) -- HackerRank, ...

Singapore named top container port under new global benchmark

SINGAPORE – Singapore has been ranked the world’s leading container port under a new benchmark published by classification society DNV and business consultancy firm Menon Economics. The Republic was ...
Nasdaq

CrowdStrike and Meta Deliver New Benchmarks for the Evaluation of AI Performance in Cybersecurity

New benchmarks define how LLMs should be tested in the SOC – measuring real threats, workflows, and outcomes to help defenders Cyber defenders face an overwhelming challenge from the influx of ...
TechCrunch

Meta’s benchmarks for its new AI models are a bit misleading

One of the new flagship AI models Meta released on Saturday, Maverick, ranks second on LM Arena, a test that has human raters compare the outputs of models and choose which they prefer. But it seems ...
Qatar Tribune on MSN

Qatar Airways sets new benchmark with over 100 Starlink-enabled widebody aircraft

The World’s Best Airline has accelerated its Starlink installation programme to deliver the fastest, gate-to-gate* Wi-Fi rollout on a widebody fleet – ahead of schedule ...