LLM Model Comparison & Evaluation
Open
area:ff-expert
time:TBD
- Dominant language
- JavaScript
- Stars
- 400
- Forks
- 89
- Avg merge
- 1d 20h
- Merged PRs (30d)
- 149
Description
Parent: FlowFuse/product#68
Benchmark alternative LLM models against current gpt-4.1-mini for Expert flow generation. Evaluate Gemini Mini/Flash, Claude Sonnet, GPT-4.1 on quality, speed, cost, and schema adherence. LangChain is already model-agnostic.
Contributor guide
Assessment
This issue has not been assessed yet.