Vals AI News

Alibaba's Qwen 3.7 Max evaluated across our benchmark suite

Google's Gemini 3.5 Flash evaluated across our benchmark suite

Vals Index and Multimodal Index v1.1 Released

Finance Agent v2 Released

Vals Index and Multimodal Index Methodology Update

Mistral Medium 3.5 lands #32 on the Vals Index

Grok 4.3 Released

Qwen 3.6 27B lands #22 on the Vals Index!

DeepSeek V4 Released

GPT 5.5 evaluated across our benchmark suite