Leanstral 1.5

Leanstral 1.5

Mistral AI
LongCat-2.0

LongCat-2.0

LongCat
+
+

Related Products

  • TrustInSoft Analyzer
    6 Ratings
    Visit Website
  • Gemini Enterprise Agent Platform
    983 Ratings
    Visit Website
  • dbt
    263 Ratings
    Visit Website
  • Member365
    48 Ratings
    Visit Website
  • JetBrains Junie
    12 Ratings
    Visit Website
  • Detrack
    148 Ratings
    Visit Website
  • CampaignTrackly
    57 Ratings
    Visit Website
  • Google AI Studio
    30 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Yeastar P-Series PBX System
    116 Ratings
    Visit Website

About

Leanstral 1.5 is an Apache-2.0 licensed model for practical proof engineering in Lean 4, built to make formal verification more powerful and accessible. With 119B total parameters and only 6B active parameters, it delivers a major performance upgrade for theorem proving, agentic proof engineering, and real-world code verification. Leanstral 1.5 was trained through a three-stage process: mid-training, supervised fine-tuning, and reinforcement learning with CISPO. In the multiturn environment, the model receives a theorem statement, submits a proof, gets Lean compiler feedback, and refines its approach until the proof compiles or the budget is exhausted. In the code agent environment, Leanstral works like a developer in a raw filesystem: it edits files, runs bash commands, and uses the Lean language server to inspect goals, errors, and type information in real time.

About

LongCat-2.0 is a 1.6 trillion total-parameter Mixture-of-Experts language model built on AI ASIC superpods, with about 48 billion parameters activated per token and strong performance across coding and agentic tasks. It is a substantial step up from previous LongCat models, combining large-scale sparse architecture with dedicated post-training for real-world software engineering, tool use, long-context reasoning, and multi-step agent workflows. LongCat-2.0 is trained and deployed entirely on AI ASIC superpods, with pretraining spanning more than 35 trillion tokens and millions of accelerator-hours, demonstrating frontier-scale training on alternative hardware platforms. To strengthen long-horizon tasks, the model introduces LongCat Sparse Attention and is trained on hundreds of billions of tokens of 1M-context data, giving it native support for ultra-long context tasks and reliable long-document understanding.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Formal methods engineers and Lean 4 researchers who need an open model for theorem proving, proof debugging, and real-world code verification

Audience

AI coding-platform teams that need a large open MoE model for agentic coding, long-context reasoning, tool use, and complex software automation

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version
Free Trial

Pricing

No information available.
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Mistral AI
Founded: 2023
France
mistral.ai/news/leanstral-1-5/

Company Information

LongCat
Founded: 2023
China
longcat.chat/blog/longcat-2.0/

Alternatives

Leanstral

Leanstral

Mistral AI

Alternatives

Claude Opus 4.6

Claude Opus 4.6

Anthropic
Claude Opus 4.7

Claude Opus 4.7

Anthropic
DeepSWE

DeepSWE

Agentica Project
Claude Opus 4.8

Claude Opus 4.8

Anthropic
SWE-1.5

SWE-1.5

Cognition
GLM-5

GLM-5

Zhipu AI
Command R+

Command R+

Cohere AI

Categories

Categories

Integrations

Claude Code
Hermes Agent
OpenClaw

Integrations

Claude Code
Hermes Agent
OpenClaw
Claim Leanstral 1.5 and update features and information
Claim Leanstral 1.5 and update features and information
Claim LongCat-2.0 and update features and information
Claim LongCat-2.0 and update features and information