Vals

Independent evaluator Vals found that Google's Gemini 3.8 Flash scored 71.7% on BioMysteryBench's human-solvable tasks and 21.6% on its hard tasks in production runs, versus the 88.8% and 56.5% Google…

Andreessen Horowitz (a16z) has invested in Vals, a startup building an evaluation platform that tests AI models on real-world tasks rather than academic benchmarks, aiming to become an independent sco…