# Mistral Medium 3.5

26 Hacker News commenters recommended Mistral Medium 3.5 and 28 criticized it, November 2025 to November 2026. It was recommended in 8 of 13 months.

**Verdict:** Fast, cheap, and good enough for many everyday coding and writing tasks; the common caveat is that it trails newer models.

## Why people recommend it

- Good enough for many tasks (4 comments): "Mistral's medium is absolutely good enough to help with a ton of coding tasks." ([source](https://news.ycombinator.com/item?id=49949244)) "within a few percent of SOTA that might be good enough for a lot of people" ([source](https://news.ycombinator.com/item?id=47950000)) "lower sized models, lower costs, overall good enough performance" ([source](https://news.ycombinator.com/item?id=47958725))
- Cheap, low-cost pricing (3 comments): "and Mistral Medium down to some Qwen 3.6 35B for effectively peanuts compared to Anthropic." ([source](https://news.ycombinator.com/item?id=48691405)) "most aggressive open-weight pricing I've seen anywhere near frontier capability" ([source](https://news.ycombinator.com/item?id=47951064)) "lower sized models, lower costs, overall good enough performance" ([source](https://news.ycombinator.com/item?id=47958725))
- Open weight, self-hostable (2 comments): "it's open weight and is tiny compared to a lot of it's competitors" ([source](https://news.ycombinator.com/item?id=47951344)) "This model is a very good option for enterprise self host." ([source](https://news.ycombinator.com/item?id=47951167))
- Better than earlier Mistral models (2 comments): "The new Mistral Medium 3.5 is also a big improvement over devstral-2" ([source](https://news.ycombinator.com/item?id=48742353)) "It's giving me better results than mistral-large for my use cases." ([source](https://news.ycombinator.com/item?id=47951097))

## What people warn about

- Trails newer open models (5 comments): "Unfortunately they only compare to old “all other open models”. There are probably over 10 other open models better than it by now." ([source](https://news.ycombinator.com/item?id=47950332)) "the fact the Gemma 4 26B A4B I'm running locally can blow it out of the water doesn't give me high confidence for the model" ([source](https://news.ycombinator.com/item?id=47951211)) "When I try other html / js prompts it also lacks behind china models from over half a year ago." ([source](https://news.ycombinator.com/item?id=47952598))
- Feels dated for current standards (3 comments): "considering the model is getting a bit old, I wouldn't expect them to keep offering it forever" ([source](https://news.ycombinator.com/item?id=47954504)) "Mistral large 3/medium 3.5/small 4 have all been pretty dated for a while" ([source](https://news.ycombinator.com/item?id=50302874)) "twice the European counterpart (albeit dated for today's standards?)" ([source](https://news.ycombinator.com/item?id=48944278))
- Priced high for its performance (2 comments): "This particular Mistral Medium looks to be uncompetitive at that pricing." ([source](https://news.ycombinator.com/item?id=47950521)) "new Medium 3.5 is far more expensive than previous Mistral models" ([source](https://news.ycombinator.com/item?id=48327526))
- Benchmark results questioned (2 comments): "It's SWE-Bench Verified. A benchmark Open-AI stopped using two months ago due to contamination." ([source](https://news.ycombinator.com/item?id=47949882)) "Not really. The benchmarks are based on F8_E4M3 and you’re not running that on any Mac." ([source](https://news.ycombinator.com/item?id=47953884))

## 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

## Where to get it

- [Visit the official site](https://mistral.ai/)

## Cite as

Hacker Approved, "Mistral Medium 3.5", https://hackerapproved.com/p/mistral-medium-3-5/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).