Leanstral 1.5
vetronauta
153 points
45 comments
June 30, 2026
Related Discussions
Found 5 related stories in 823.0ms across 14,015 title embeddings via pgvector HNSW
- Leanstral 1.5: Proof abundance for all programLyrique · 159 pts · July 03, 2026 · 70% similar
- Leanstral: Open-source agent for trustworthy coding and formal proof engineering Poudlardo · 407 pts · March 16, 2026 · 60% similar
- Mistral Small 4 pember · 56 pts · March 16, 2026 · 55% similar
- GLM-5.1: Towards Long-Horizon Tasks zixuanlimit · 481 pts · April 07, 2026 · 50% similar
- Mistral OCR 4 meetpateltech · 449 pts · June 23, 2026 · 49% similar
Discussion Highlights (8 comments)
__natty__
Discussion about Leanstral 1: https://news.ycombinator.com/item?id=47404796
doctorpangloss
Real talk, does anyone use anything from Mistral because it performs the best, by whatever secular metric of your choosing? Or is it only used "because EU"? Just focus on answering the question. I wonder if anyone has observed it perform better on any objective metric in any rigorous setting.
esafak
Is this useful for specifying programs too or only theorems?
impodimium
Interesting that this only specialized for Lean4 and not for similar like Coq
henryrobbins00
What a coincidence! I just released OpenATP earlier today. OpenATP is an open-source Python package and CLI for agentic automated theorem provers. It includes support for Leanstral with Mistral’s Vibe harness. The previous production Leanstral model was deprecated on May 22nd. I will update the package to point to Leanstral 1.5 ASAP! GitHub: https://github.com/henryrobbins/open-atp Docs: https://open-atp.henryrobbins.com
pmarreck
Lean 4 and Idris 2 are underrated, and likely great for LLM's to code in (since they provide additional guarantees)
Grimblewald
Got curious, sign up, add money to account, try to use. Can't, it's a labs model. Fine, let's enable labs. Can't, unspecified error. Fine, lets contact customer support as instructed, can't no customer support, just a half-assed FAQ, that seems vibe-coded and searched poorly, totally irrelevant answers coming up for all queries tried. Then it hit me: If AI makes good customer support, then why does no AI company use theirs to provide customer support?
c7b
I'm not sure I understand the Weights policy. This site says the weights are Apache-licensed, suggesting it's open weights. But I can't find a download link. Their Huggingface profile seems to only provide an earlier snapshot [0]. Any pointers on whether/where we can or will be able to download the weights? [0] https://huggingface.co/mistralai/Leanstral-2603