# Sol High

12 Hacker News commenters recommended Sol High and 4 criticized it, November 2025 to November 2026. It was recommended in 3 of 13 months.

**Verdict:** Recommended as a sharp, reliable reasoning model that gets tasks right in one pass. Critics find the xhigh setting too slow for daily use and report uneven benchmark results.

## Why people recommend it

- Strong preference over other models (4 comments): "Sol high being a substantially better model" ([source](https://news.ycombinator.com/item?id=49289650)) "Right now, sol-xhigh is my favorite model." ([source](https://news.ycombinator.com/item?id=49277073)) "Agree that Sol is a great model." ([source](https://news.ycombinator.com/item?id=49417263))
- Gets complex tasks fully right (2 comments): "completed it in one go with zero edge cases remaining." ([source](https://news.ycombinator.com/item?id=49218844)) "nothing below that works correctly" ([source](https://news.ycombinator.com/item?id=49276810))
- Comfortable for all-day use (2 comments): "I could keep using these models forever even if they did not significantly improve" ([source](https://news.ycombinator.com/item?id=49412919)) "I find I can pretty comfortable use Sol high most of the day" ([source](https://news.ycombinator.com/item?id=49579001))

## Alternatives hackers recommend

- [Claude Opus](https://hackerapproved.com/p/claude-opus.md): 3331 recommend
- [OpenAI GPT](https://hackerapproved.com/p/gpt-5-5.md): 1205 recommend
- [Claude Sonnet](https://hackerapproved.com/p/claude-sonnet.md): 854 recommend
- [DeepSeek V4 Flash](https://hackerapproved.com/p/deepseek-v4-flash.md): 828 recommend
- [Fable](https://hackerapproved.com/p/fable.md): 823 recommend

## Cite as

Hacker Approved, "Sol High", https://hackerapproved.com/p/sol-high/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).