← All projects
classifier-bakeoff
alpersonalwebsite/classifier-bakeoff Python Eval & Align
rank#399
Head-to-head bakeoff of LLM classifiers (Jev, OpenAI Decisions API, Claude) on synthetic lead triage: accuracy, tokens, cost, and latency through OpenRouter.
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last push
- today
Star history starts building from the first daily refresh.
benchmarkclaudeevaluationjevjev-aillmopenaiopenrouterpythontext-classification