Mistral · mistral.ai
Since its launch, Leanstral has offered an open, practical approach to proof engineering in Lean 4
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Leanstral 1.5 saturates miniF2F, solves 587/672 PutnamBench problems, and achieves a new state-of-the-art of %87 on FATE-H and 34% on FATE-X.
Key facts
- On PutnamBench, it edges out Seed-Prover 1.5 high by 7 problems at far lower cost: about $4 per problem, against an estimated $300 or more for Seed-Prover, whose high setting runs with a budget of 10
- Leanstral 1.5 saturates miniF2F, solves 587/672 PutnamBench problems, and achieves a new state-of-the-art of %87 on FATE-H and 34% on FATE-X
- Leanstral 1.5, a free Apache-2.0 licensed model with 6B active parameters, delivers a major performance upgrade in formal verification, saturating miniF2F, solving 587/672 PutnamBench problems
- Leanstral 1.5 lifts pass@1 on the benchmark from 21.9 to 28.9 and pass@8 from 31.9 to 43.2, surpassing Opus 4.6's 39.6 at one-seventh the cost
Summary
Leanstral 1.5, a free Apache-2.0 licensed model with 6B active parameters, delivers a major performance upgrade in formal verification, saturating miniF2F, solving 587/672 PutnamBench problems, and achieving state-of-the-art results on FATE-H (87%) and FATE-X (34%). Since its launch, Leanstral has offered an open, practical approach to proof engineering in Lean 4. Leanstral 1.5 goes through a three-stage process: mid-training, supervised fine-tuning, and reinforcement learning with CISPO. In the multiturn environment, the model is given a theorem statement and must either prove or disprove it.