Models
| Provider | Model | Checkpoint | Notes |
|---|---|---|---|
| OpenAI | GPT-6 Luna | gpt-6-luna | Default |
| GPT-6 Sol | gpt-6-sol | ||
| GPT-5.6 Luna | gpt-5.6-luna | Deprecated | |
| GPT-5.4 | gpt-5.4-2026-03-05 | Deprecated | |
| GPT-5.2 | gpt-5.2-2025-12-11 | Deprecated | |
| GPT-5 | gpt-5-chat-latest | Deprecated | |
| GPT-4.1 | gpt-4.1-2025-04-14 | Deprecated | |
| GPT-4o | gpt-4o-2024-11-20 | Deprecated | |
| Anthropic | Claude Opus 5.5 | claude-opus-5-5 | |
| Claude Opus 4.8 | claude-opus-4-8 | Deprecated | |
| Claude Sonnet 4.5 | claude-sonnet-4-5-20250929 | Deprecated | |
| Claude Sonnet 4.0 | claude-sonnet-4-20250514 | Deprecated | |
| Gemini 3.8 Flash | gemini-3.8-flash | ||
| Gemini 3.5 Flash | gemini-3.5-flash | Deprecated | |
| Gemini 3.1 Pro | gemini-3.1-pro-preview | Deprecated | |
| Gemini 3 Pro | gemini-3-pro-preview | Deprecated | |
| Gemini 2.5 Pro | gemini-2.5-pro | Deprecated |
How to choose
| Models | Speed | Answer Streaming |
|---|---|---|
| GPT-6 Luna | Fastest | ✅ |
| GPT-6 Sol | Fast | ✅ |
| Gemini 3.8 Flash | Medium | ✅ |
| Claude Opus 5.5 | Slow | ✅ |
- Every model here handles technical interview questions with plenty of room to spare, so the faster model is usually the right pick over the more capable one.
- GPT-6 Luna is the fastest and starts returning answers soonest.
- GPT-6 Sol is OpenAI’s balanced tier: smarter than GPT-6 Luna, at the cost of some speed.
- Gemini 3.8 Flash is slower than both GPT models.
- Claude Opus 5.5 is the slowest, so answers take longer to start showing up.
How are models updated
- When a new model is released, it will be added within one or two weeks.
- If a new model is in preview stage or not stable, its previous stable generation will be kept.
- A deprecated model is never removed abruptly: a request for it is answered by the latest model of the same family (for example, any GPT Sol version by the latest GPT Sol), or else by the latest model from the same provider, so older extension versions keep working.
Last updated on