Testing Gemini 3.8 Flash in Cursor with a CRM Smoke Test
Melvin Vivas · X post · 2026-09-03 · Open on X
Topics: Evaluation (Evals) & Testing, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator tested Gemini 3.8 Flash in Cursor using his own CRM app 'smoke test'. It was fast and built every requested feature, but it made a UI mistake on a modal background. He finds it worth trying and will keep testing it on real work.
Key points
- Keep a personal smoke-test app (here a CRM) for judging new models the same way each time.
- Pros: Gemini 3.8 Flash is fast and implemented all the requested features.
- Cons: it made a UI mistake on the modal background, which he says frontier models shouldn't make anymore.
- Verdict: worth trying; keep testing on real work before switching.
Resources mentioned
- Gemini 3.8 Flash · tool · deepmind.google · free
Google's fast, low-cost Gemini model, suited to auxiliary tasks like web browsing and vision.
Also in: Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), Gemini 3.8 Flash Available in Cursor CLI (Melvin Vivas on X · notes), Models That Work With the Hermes Agent for Personal Productivity (Melvin Vivas on X · notes), Cut Hermes Agent Token Costs with Gemini Flash as an Auxiliary Model (Melvin Vivas on X · notes) - Cursor · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
AI-native code editor (VS Code with AI built in).
Also in: Finding Cursor Cloud Agents After the Cursor–X Unification (Melvin Vivas on X · notes), Overnight notebook generation with Grok Bot, Cursor cloud and Grok 4.7 (Melvin Vivas on X · notes), Gemini 4 Argon in Cursor: CursorBench Score and Pricing (Melvin Vivas on X · notes), SpaceX AI / Cursor Ambassador Program Waitlist (Melvin Vivas on X · notes) and 135 more
Try this
- Try Gemini 3.8 Flash for coding and check the UI details it produces.
- Test new models on your own repeatable smoke-test app.
- Build a small CRM app as a reusable smoke test for comparing coding models.
More in Evaluation (Evals) & Testing
- Be Skeptical of Model Leaderboards: Muse Spark vs Astra
- Personal Smoke Test for New Models: "Make a CRM App"
- Compare Model Outputs with Artificial Analysis MicroEvals
- Cohere Parse: Pricing vs Parse Bench Score
- Evaluation for AI Engineering: Free Full Guide (Resource Share)
- Local Data Studio: Inspect Private Datasets Without Hugging Face Pro