Latent Space· Latent.Space·· 2 d ago
[AINews] AI Engineer NYC: Gemini 4 Argon, Vals AI Benchmarks
[AINews] AI Engineer NYC: Gemini 4 Argon, Vals AI Benchmarks
AI summary
Gemini 4 Argon went GA today, but we already gave it title story 2 weeks ago and most benchmarks, like CursorBench, simply independently confirm their claims.
Selection record
Threshold 76Media and individualsFirst 78Second 78
AdmittedSum of both 156 ≥ twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：正文详述Gemini 4等AI模型发布与评测
- Why it was chosen
- Round-up of the Gemini 4 Argon launch, evaluations of several models and agent infrastructure moves, giving a quick read on the day's frontier model and engineering shifts.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Latent Space · latent.space