Home
vals.ai · 128 words · saved by 3 readers
Private, domain-specific benchmarks in legal, tax, and finance.
Independent Evaluation, Unbiased Benchmarks Testing AI on Real-World Tasks We benchmark the world's leading AI models on economically valuable tasks such as finance, software, and frontier risk like cybersecurity, recursive self improvement and mental health. We run all of our own evaluations and create many of our benchmarks in-house. •Sep 21, 2026 Latest Reports Recent benchmark releases and model evaluations. Sep 21, 2026 xAI's Grok 4.7 evaluated across our benchmark suite Vals benchmarksIndustry partnerAcademic benchmarks Industry Leaderboard Model performance on different…
saved by
related reading
- Vals AIvals.ai
- BenchmarkList: Track the Frontier of AI Capabilitiesbenchmarklist.com
- benchmarks.bio — Agentic benchmarks on messy, real-world biological databenchmarks.bio
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Measuring the performance of our models on real-world tasks | OpenAIopenai.com
- METRmetr.org
- Explore | alphaXivalphaxiv.org
- CAIS AI Dashboarddashboard.safe.ai
- Grok 4 Various Things — LessWronglesswrong.com
- AI Agent Benchmark for Real-World Professional Workflowsagents-last-exam.org
- AI Values Dashboardvalues.safe.ai
- Robocurve — Real-world evaluations of physical AIrobocurve.org