Model evaluation specialists

AI news and practical stories for this audience.

Latest stories

DevelopersOctober 3, 2026

Hugging Face introduces Open TTS Leaderboard for objective model evaluation

Hugging Face’s Open TTS Leaderboard compares open TTS models using WER/CER, RTFx, TTFA and speaker similarity. Its scores complement rather than replace human preference rankings.

Hugging Face↗

ModelsSeptember 30, 2026

Anthropic: GLM-5.3 built exploits, while its safeguards were bypassed in simulations

Anthropic says GLM-5.3 built exploits in its tests and that distinct methods bypassed its built-in safeguards in simulations without executing code.

Anthropic↗