iammrduncan/typesafe-ai-benchmark
Compares LLM structured output with Jev on latency, cost, and judgment quality.
TypeScript
Jev Benchmarks and Evaluation Tools
TypeSafe's published speed, cost, and accuracy numbers come from its own evaluations. The projects here measure Jev independently, check whether its confidence scores are calibrated on real datasets, and help you pick a threshold for your own data.
If you plan to automate decisions based on Jev's confidence, start here.
4 projects
AbdelStark/jev-benchmarks
Probability-aware evaluation: calibration, and how much work can be automated at a fixed error budget.
Python
Janus
★ 2FirasSX914/Janus
Measures Jev's calibration and confidence-based routing on Banking77 and Web of Science.
Python
jevcal
★ 1abhixhek/jevcal
Picks the confidence threshold that meets your accuracy target on your own data, and fails CI when a model update breaks it.
Python
Other categories
- Community SDKs
- Libraries & Integrations
- Agent Integrations (MCP & Skills)
- Coding Agents & Developer Tools
- Guardrails & Safety
- Model Routing
- Command-Line Tools
- Browser & Computer Use
- Data & Observability
- Search & Knowledge Graphs
- Apps & Browser Extensions
- Open Models & Reproductions
- Games & Real-Time Demos
- Finance
Get new Jev projects every week
New Jev releases, pricing changes, and the best new projects, once a week. No spam; unsubscribe anytime.
Powered by Buttondown. See our privacy policy.