Benchmarks

5 articles

SORT BY

Claude Opus 4.8 Fails Legal Honesty Test in New Benchmark

Claude Opus 4.8 Fails Legal Honesty Test in New Benchmark

Alibaba Confirms It Built HappyHorse, the AI Video Model Topping Charts

Alibaba Confirms It Built HappyHorse, the AI Video Model Topping Charts

Anthropic's Opus 4.6 Jumps AI Agent Benchmark 60% in Weeks

Anthropic's Opus 4.6 Jumps AI Agent Benchmark 60% in Weeks

Anthropic's Opus 4.5 breaks coding barriers with Chrome, Excel launch

Anthropic's Opus 4.5 breaks coding barriers with Chrome, Excel launch

Apple M5 MacBook Pro Review: Minor Speed Bump, Major Value

hardware9 mths ago

Apple M5 MacBook Pro Review: Minor Speed Bump, Major Value